Initial commit

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+replay.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Ant-v4
     metrics:
     - type: mean_reward
-      value: 986.69 +/- 0.92
+      value: 4867.74 +/- 1756.02
       name: mean_reward
       verified: false
 ---

SAC-Ant-v4.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f66e6a6e37a9fe6fa9f52e5066d74d4c12e61395a9ff6a11086081e719ad093c
-size 1540118
+oid sha256:5735696ef4a4c724941f4036b55c4156f56dc00a8adae1d1a402a19d58763b01
+size 3381810

SAC-Ant-v4/actor.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08ed154c1a087db3c25e8b2e3701fdfda2501b3ffaa57cfb6017a176f66133ed
-size 1120
+oid sha256:96acc34126daa0f0da4c70dccbd4ba2db86a375971e8b677d00af4cb231311a6
+size 623182

SAC-Ant-v4/critic.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:453512d2e157cdd727057101e5ca2d541de68d713ad01bca41dd0469dd29be5c
-size 1120
+oid sha256:71faf9a5d2349452df584ae43bc761ed022dd9dd30be88572407d36805bff02a
+size 1213866

SAC-Ant-v4/data

@@ -5,41 +5,86 @@
         "__module__": "stable_baselines3.sac.policies",
         "__annotations__": "{'actor': <class 'stable_baselines3.sac.policies.Actor'>, 'critic': <class 'stable_baselines3.common.policies.ContinuousCritic'>, 'critic_target': <class 'stable_baselines3.common.policies.ContinuousCritic'>}",
         "__doc__": "\n    Policy class (with both actor and critic) for SAC.\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` when using gSDE to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param clip_mean: Clip the mean output when using gSDE to avoid numerical instability.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    :param n_critics: Number of critic networks to create.\n    :param share_features_extractor: Whether to share or not the features extractor\n        between the actor and the critic (this saves computation time)\n    ",
-        "__init__": "<function SACPolicy.__init__ at 0x13395f1a0>",
-        "_build": "<function SACPolicy._build at 0x13395f7e0>",
-        "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x13395f880>",
-        "reset_noise": "<function SACPolicy.reset_noise at 0x13395f920>",
-        "make_actor": "<function SACPolicy.make_actor at 0x13395f9c0>",
-        "make_critic": "<function SACPolicy.make_critic at 0x13395fa60>",
-        "forward": "<function SACPolicy.forward at 0x13395fb00>",
-        "_predict": "<function SACPolicy._predict at 0x13395fba0>",
-        "set_training_mode": "<function SACPolicy.set_training_mode at 0x13395fc40>",
+        "__init__": "<function SACPolicy.__init__ at 0x11f55f240>",
+        "_build": "<function SACPolicy._build at 0x11f55f880>",
+        "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x11f55f920>",
+        "reset_noise": "<function SACPolicy.reset_noise at 0x11f55f9c0>",
+        "make_actor": "<function SACPolicy.make_actor at 0x11f55fa60>",
+        "make_critic": "<function SACPolicy.make_critic at 0x11f55fb00>",
+        "forward": "<function SACPolicy.forward at 0x11f55fba0>",
+        "_predict": "<function SACPolicy._predict at 0x11f55fc40>",
+        "set_training_mode": "<function SACPolicy.set_training_mode at 0x11f55fce0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x133967740>"
+        "_abc_impl": "<_abc._abc_data object at 0x11f5786c0>"
     },
     "verbose": 0,
     "policy_kwargs": {
         "use_sde": false
     },
-    "num_timesteps": 0,
-    "_total_timesteps": 0,
+    "num_timesteps": 975000,
+    "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 0.0,
+    "start_time": 1718033158578114641,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
-    "_last_obs": null,
-    "_last_episode_starts": null,
-    "_last_original_obs": null,
-    "_episode_num": 0,
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVTQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJbYAAAAAAAAAIsIIRAUDOE/O7C9Q7BR7j/VNfthvbSyPzyXVpvJ7bO/lpQiAKhL0z8D18h+CUbhvxWlo6uMvOA/FIRu+MXL4L9fhnvbErfgvw6xZ2dVQ+E/sqde5gWw4L8hLofHoszgv9uqvWEFs+A/JCVXXeTsFUDdwjvn5+P1P8hct10pWOa//2kCer+n/b8JnopGCvLxPyWcLDIYsPC/uF7qCg8W4D9GEfMuy6mKP/SL0A8F93e/JCaiknEVeT/Ov4LgNiv0v2rmR+LxdHG/VCNSBpANiz/RP4Nzf3gEwJSMBW51bXB5lIwFZHR5cGWUk5SMAmY4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsbhpSMAUOUdJRSlC4="
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVTQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJbYAAAAAAAAANdz/rVocOI/TCP9PzEW7j8JmtfHbs20P4sWpj/mDrG/CxKqlxu81D9eKqDgtlThv4mBY4Niq+A/dMjM7ZfI4L9z2UeORLvgv6DD+Gup8Nw/YcnKGpOt4L8+dx06QNTgvzeSjp0Xa+M/kHYDb5KfFUCuHXM4YeDtP/KzQtAV7+i/8NEW4/beir8QOUIqevntv2a6GaOEVOm/uol/bG0OBcBWN6ttO4O2P3skrpSJfWQ/MQYHE87JUz/0yZSSF2kVQHhwoXjkjhm/QtJBbSrCUD85fNoChIXGv5SMBW51bXB5lIwFZHR5cGWUk5SMAmY4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsbhpSMAUOUdJRSlC4="
+    },
+    "_episode_num": 1206,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": 1.0,
+    "_current_progress_remaining": 0.02500100000000005,
     "_stats_window_size": 100,
-    "ep_info_buffer": null,
-    "ep_success_buffer": null,
-    "_n_updates": 0,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVQQwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQKyG15GBnSSMAWyUTdACjAF0lEdAu0BWnjyWiXV9lChoBkdAtKDgQUYbbWgHTegDaAhHQLtHmssQNCt1fZQoaAZHQLU3dGX5WR1oB03oA2gIR0C7TtvSMLncdX2UKGgGR0C0ePtEPUayaAdN6ANoCEdAu1YcJiRW93V9lChoBkdAtEiDUy57PmgHTegDaAhHQLtdcTkhib51fZQoaAZHQLThbIFeOXFoB03oA2gIR0C7aN/A9FF2dX2UKGgGR0C1TgP9pAUtaAdN6ANoCEdAu3AlEa2nbnV9lChoBkdAs8x9p35eq2gHTegDaAhHQLt3Z2xptaZ1fZQoaAZHQLYTPCZnctZoB03oA2gIR0C7fq62SdOJdX2UKGgGR0C1k6XmRvFWaAdN6ANoCEdAu4XtDSgGr3V9lChoBkdAtXuClZX+2mgHTegDaAhHQLuRQ0xubZx1fZQoaAZHQLHzoszVMEloB01qA2gIR0C7l5RyfcvedX2UKGgGR0C1Mf78m8dxaAdN6ANoCEdAu57eFIuoP3V9lChoBkdAtFqEeGO+7GgHTegDaAhHQLumHmWMS9N1fZQoaAZHQLR6mh3JPqNoB03oA2gIR0C7rWuqBErodX2UKGgGR0C0lnilzltCaAdN6ANoCEdAu7hL5DZ13nV9lChoBkdAtSGIvmHP/2gHTegDaAhHQLu/mxFAmiR1fZQoaAZHQLS5+rbQC0ZoB03oA2gIR0C7xtdjkMkQdX2UKGgGR0C1oWGh/RVqaAdN6ANoCEdAu84UlD4QBnV9lChoBkdAtWxwEV32VWgHTegDaAhHQLvVU/d69kB1fZQoaAZHQLN2M+OOsDJoB03oA2gIR0C74LpNKyv+dX2UKGgGR0C0sFd5IH1OaAdN6ANoCEdAu+gDtIClrXV9lChoBkdAtEu5rKvFFWgHTdkDaAhHQLvvKtXgccV1fZQoaAZHQLYMaqD9OypoB03oA2gIR0C79m+uvECOdX2UKGgGR0C0TEfw3HaOaAdN6ANoCEdAu/3L8qFyrHV9lChoBkdAtMbnLr5ZbWgHTegDaAhHQLwJAyxiXpp1fZQoaAZHQLQ7W6y0KJFoB03oA2gIR0C8EEHT7VJ+dX2UKGgGR0C0jUCfxtpFaAdN6ANoCEdAvBeJggHNYHV9lChoBkdAtL4hCMPz4GgHTegDaAhHQLwexaRp1zR1fZQoaAZHQLTHD7mdRSBoB03oA2gIR0C8JgCy2QXAdX2UKGgGR0C06N9fTkQxaAdN6ANoCEdAvDFfmbLEDXV9lChoBkdAtN6lEx7AtWgHTegDaAhHQLw4qfNRm9R1fZQoaAZHQLSJwV7Qb+9oB03oA2gIR0C8P+mxQizLdX2UKGgGR0C0+35oXbdraAdN6ANoCEdAvEc5OwgTy3V9lChoBkdAs+sbi83+/GgHTegDaAhHQLxOgv2oNut1fZQoaAZHQLSFiuKXOW1oB03oA2gIR0C8WfAbuMMrdX2UKGgGR0CzYWavaDf4aAdN6ANoCEdAvGExh3JPqXV9lChoBkdAtIBrlRxcV2gHTegDaAhHQLxobDsMRYl1fZQoaAZHQJ32fKDCgsdoB01+AWgIR0C8azIkzGgjdX2UKGgGR0Cixk4qPOpsaAdNvQFoCEdAvG5tAD7qIXV9lChoBkdAo54AQvpQlGgHTegDaAhHQLx1vGIbfgt1fZQoaAZHQLSHjQPZqVRoB03oA2gIR0C8gSkFW4mUdX2UKGgGR0C06Whc7hegaAdN6ANoCEdAvIhpUOuq3nV9lChoBkdAtFbX2oNutWgHTegDaAhHQLyPuq1w5vN1fZQoaAZHQLVZJy9mHxloB03oA2gIR0C8lw4gzP8idX2UKGgGR0C13ecZgogFaAdN6ANoCEdAvJ5ZrFfiP3V9lChoBkdAtabJO58Sf2gHTegDaAhHQLypm75mAb11fZQoaAZHQLYBQiblRxdoB03oA2gIR0C8sObhrFfidX2UKGgGR0C1OQNFvybyaAdN6ANoCEdAvLgok+otMHV9lChoBkdAqBsNr9ETg2gHTTMCaAhHQLy8Pehf0Ep1fZQoaAZHQLU4swztTk1oB03oA2gIR0C8w3yyIHkcdX2UKGgGR0C05qksasIWaAdN6ANoCEdAvMrIPuogm3V9lChoBkdAaDqfh/Aj6mgHSzhoCEdAvMswVXV9W3V9lChoBkdAtN+cGLUCrGgHTegDaAhHQLzWnYW+GoJ1fZQoaAZHQLO2PndO6/ZoB03oA2gIR0C83ejCk43ndX2UKGgGR0C1XYD544ZNaAdN6ANoCEdAvOU8s+V1OnV9lChoBkdAtNhUD0UXYWgHTegDaAhHQLzskDEm6Xl1fZQoaAZHQLXSB6bvw3JoB03oA2gIR0C8883Yg7o0dX2UKGgGR0C0Mopswco6aAdN6ANoCEdAvP8azru6VnV9lChoBkdAtK6B1q33H2gHTegDaAhHQL0GZgflp491fZQoaAZHQLXca4UeuFJoB03oA2gIR0C9DaVejVQRdX2UKGgGR0C1PBkG/vfCaAdN6ANoCEdAvRT5ul41P3V9lChoBkdAtH0QibDuSmgHTegDaAhHQL0cNu1F6Rh1fZQoaAZHQFopnHeaa1FoB0sqaAhHQL0chfVZs9B1fZQoaAZHQLUql5ZKWcBoB03oA2gIR0C9J1xSHdoGdX2UKGgGR0C1eAEL2HtXaAdN6ANoCEdAvS6w7T2FnXV9lChoBkdAtUKr1XeWOmgHTegDaAhHQL019rqt5lh1fZQoaAZHQLT/rjYqXnhoB03oA2gIR0C9PTzt5UtJdX2UKGgGR0C0HlO2Zy+6aAdN6ANoCEdAvUSGJl8PWnV9lChoBkdAs55Ul9jPOmgHTegDaAhHQL1P2RJVbRp1fZQoaAZHQLWfmMY/FBJoB03oA2gIR0C9Vxp6Y3NtdX2UKGgGR0C0rQbwrlNlaAdN6ANoCEdAvV5bsMRYinV9lChoBkdAtaYb8Lron2gHTegDaAhHQL1lpgQYk3V1fZQoaAZHQLUdCeANG3FoB03oA2gIR0C9bOek1uR+dX2UKGgGR0C2A9Ma0hNeaAdN6ANoCEdAvXhR7ngYQHV9lChoBkdAtO8GHZbpvGgHTegDaAhHQL1/qJPZZjh1fZQoaAZHQLPw6as6q81oB03oA2gIR0C9hu+RLbpNdX2UKGgGR0C0aMD6JqIraAdN6ANoCEdAvY4wzxgAqHV9lChoBkdAtXi555Z8r2gHTegDaAhHQL2Vc3NcGC91fZQoaAZHQLUmXzw+dLBoB03oA2gIR0C9oNRYmsvJdX2UKGgGR0C1Us+5WilBaAdN6ANoCEdAvagRVBD5TXV9lChoBkdAtcx0MH8jzWgHTegDaAhHQL2vUC53C9B1fZQoaAZHQLR7ww3o9s9oB03oA2gIR0C9towRf4RFdX2UKGgGR0C0xi2bwz+FaAdN6ANoCEdAvb3XzPKMenV9lChoBkdAtgInVH4GlmgHTegDaAhHQL3JWTwlSjx1fZQoaAZHQLUksT3qRlpoB03oA2gIR0C90JovN/vwdX2UKGgGR0C1Vp2EoOQRaAdN6ANoCEdAvdfYuHvc8HV9lChoBkdAtgJOPOpsGmgHTegDaAhHQL3fH81Gb1B1fZQoaAZHQLTLodUsFt9oB03oA2gIR0C95l/ra/RFdX2UKGgGR0C1d4bNnoPkaAdN6ANoCEdAvfGsHs1KoXV9lChoBkdAtP3dhfBvaWgHTegDaAhHQL3473mmtQt1fZQoaAZHQLSSlbBXS0BoB03oA2gIR0C+AC3erMkhdX2UKGgGR0C1TbJBX0XhaAdN6ANoCEdAvgdtTFVDKHV9lChoBkdAta8q8Yht+GgHTegDaAhHQL4Ovz4UN8V1fZQoaAZHQK+CfVrhzeZoB038AmgIR0C+GIMFUyYYdX2UKGgGR0C1bb71h9b5aAdN6ANoCEdAvh/CkpI+XHV9lChoBkdAd/bDCgsbvWgHS15oCEdAviBwMfA9FHV9lChoBkdAtVY+U8mrsGgHTegDaAhHQL4nq+dbxEx1fZQoaAZHQLPSBC+lCTloB03oA2gIR0C+LufSMLncdX2UKGgGR0C2FCGvwEyMaAdN6ANoCEdAvjYxl+Vkc3VlLg=="
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 964999,
+    "buffer_size": 1000000,
+    "batch_size": 256,
+    "learning_starts": 10000,
+    "tau": 0.005,
+    "gamma": 0.99,
+    "gradient_steps": 1,
+    "optimize_memory_usage": false,
+    "replay_buffer_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
+        "__module__": "stable_baselines3.common.buffers",
+        "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'next_observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'dones': <class 'numpy.ndarray'>, 'timeouts': <class 'numpy.ndarray'>}",
+        "__doc__": "\n    Replay buffer used in off-policy algorithms like SAC/TD3.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param device: PyTorch device\n    :param n_envs: Number of parallel environments\n    :param optimize_memory_usage: Enable a memory efficient variant\n        of the replay buffer which reduces by almost a factor two the memory used,\n        at a cost of more complexity.\n        See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195\n        and https://github.com/DLR-RM/stable-baselines3/pull/28#issuecomment-637559274\n        Cannot be used in combination with handle_timeout_termination.\n    :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n        separately and treat the task as infinite horizon task.\n        https://github.com/DLR-RM/stable-baselines3/issues/284\n    ",
+        "__init__": "<function ReplayBuffer.__init__ at 0x11f4d80e0>",
+        "add": "<function ReplayBuffer.add at 0x11f4d8220>",
+        "sample": "<function ReplayBuffer.sample at 0x11f4d82c0>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x11f4d8360>",
+        "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x11f4d8400>)>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x11f4ccf80>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "target_entropy": -8.0,
+    "ent_coef": "auto",
+    "target_update_interval": 1,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -57,7 +102,7 @@
     },
     "action_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
-        ":serialized:": "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",
+        ":serialized:": "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",
         "dtype": "float32",
         "bounded_below": "[ True  True  True  True  True  True  True  True]",
         "bounded_above": "[ True  True  True  True  True  True  True  True]",
@@ -68,39 +113,9 @@
         "high": "[1. 1. 1. 1. 1. 1. 1. 1.]",
         "low_repr": "-1.0",
         "high_repr": "1.0",
-        "_np_random": null
+        "_np_random": "Generator(PCG64)"
     },
     "n_envs": 1,
-    "buffer_size": 1000000,
-    "batch_size": 256,
-    "learning_starts": 10000,
-    "tau": 0.005,
-    "gamma": 0.99,
-    "gradient_steps": 1,
-    "optimize_memory_usage": false,
-    "replay_buffer_class": {
-        ":type:": "<class 'abc.ABCMeta'>",
-        ":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
-        "__module__": "stable_baselines3.common.buffers",
-        "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'next_observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'dones': <class 'numpy.ndarray'>, 'timeouts': <class 'numpy.ndarray'>}",
-        "__doc__": "\n    Replay buffer used in off-policy algorithms like SAC/TD3.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param device: PyTorch device\n    :param n_envs: Number of parallel environments\n    :param optimize_memory_usage: Enable a memory efficient variant\n        of the replay buffer which reduces by almost a factor two the memory used,\n        at a cost of more complexity.\n        See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195\n        and https://github.com/DLR-RM/stable-baselines3/pull/28#issuecomment-637559274\n        Cannot be used in combination with handle_timeout_termination.\n    :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n        separately and treat the task as infinite horizon task.\n        https://github.com/DLR-RM/stable-baselines3/issues/284\n    ",
-        "__init__": "<function ReplayBuffer.__init__ at 0x1338d0040>",
-        "add": "<function ReplayBuffer.add at 0x1338d0180>",
-        "sample": "<function ReplayBuffer.sample at 0x1338d0220>",
-        "_get_samples": "<function ReplayBuffer._get_samples at 0x1338d02c0>",
-        "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x1338d0360>)>",
-        "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x1338bbd00>"
-    },
-    "replay_buffer_kwargs": {},
-    "train_freq": {
-        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
-        ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
-    },
-    "use_sde_at_warmup": false,
-    "target_entropy": -8.0,
-    "ent_coef": "auto",
-    "target_update_interval": 1,
     "lr_schedule": {
         ":type:": "<class 'function'>",
         ":serialized:": "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"

SAC-Ant-v4/ent_coef_optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74d1021c5cb649b52c2ace173ff267c0720b1784dfe5d38035a0149c69763bf4
-size 1120
+oid sha256:11618164b66181eb7b9c27c061c1bd90f45aade8444ee7f2e898d983e7ea0d8d
+size 1940

SAC-Ant-v4/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:437f550e8569becfa2b80a68e466b5fcc7408fa61d4d65f8e95dc9ca84df308b
+oid sha256:a7818cea3d50189c9b4bdf31ef0db05ef14792dbf364f388089294bf400c1b41
 size 1523446

SAC-Ant-v4/pytorch_variables.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f230087ced10977eb37e2eb84c20a32b34f1ef28b4b91102d17cce6983fbd27
+oid sha256:8c2540f1fd9a6ecb5ac800fcf385ea8c54c9c9e92b1ceda2e1bc54525c866ac2
 size 1180

config.json

@@ -1 +1 @@
-{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnNhYy5wb2xpY2llc5SMCVNBQ1BvbGljeZSTlC4=", "__module__": "stable_baselines3.sac.policies", "__annotations__": "{'actor': <class 'stable_baselines3.sac.policies.Actor'>, 'critic': <class 'stable_baselines3.common.policies.ContinuousCritic'>, 'critic_target': <class 'stable_baselines3.common.policies.ContinuousCritic'>}", "__doc__": "\n    Policy class (with both actor and critic) for SAC.\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` when using gSDE to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param clip_mean: Clip the mean output when using gSDE to avoid numerical instability.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    :param n_critics: Number of critic networks to create.\n    :param share_features_extractor: Whether to share or not the features extractor\n        between the actor and the critic (this saves computation time)\n    ", "__init__": "<function SACPolicy.__init__ at 0x13395f1a0>", "_build": "<function SACPolicy._build at 0x13395f7e0>", "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x13395f880>", "reset_noise": "<function SACPolicy.reset_noise at 0x13395f920>", "make_actor": "<function SACPolicy.make_actor at 0x13395f9c0>", "make_critic": "<function SACPolicy.make_critic at 0x13395fa60>", "forward": "<function SACPolicy.forward at 0x13395fb00>", "_predict": "<function SACPolicy._predict at 0x13395fba0>", "set_training_mode": "<function SACPolicy.set_training_mode at 0x13395fc40>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x133967740>"}, "verbose": 0, "policy_kwargs": {"use_sde": false}, "num_timesteps": 0, "_total_timesteps": 0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 0.0, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": null, "_last_episode_starts": null, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 1.0, "_stats_window_size": 100, "ep_info_buffer": null, "ep_success_buffer": null, "_n_updates": 0, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float64", "bounded_below": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False]", "bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False]", "_shape": [27], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf]", "low_repr": "-inf", "high_repr": "inf", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "_shape": [8], "low": "[-1. -1. -1. -1. -1. -1. -1. -1.]", "high": "[1. 1. 1. 1. 1. 1. 1. 1.]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": null}, "n_envs": 1, "buffer_size": 1000000, "batch_size": 256, "learning_starts": 10000, "tau": 0.005, "gamma": 0.99, "gradient_steps": 1, "optimize_memory_usage": false, "replay_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==", "__module__": "stable_baselines3.common.buffers", "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'next_observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'dones': <class 'numpy.ndarray'>, 'timeouts': <class 'numpy.ndarray'>}", "__doc__": "\n    Replay buffer used in off-policy algorithms like SAC/TD3.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param device: PyTorch device\n    :param n_envs: Number of parallel environments\n    :param optimize_memory_usage: Enable a memory efficient variant\n        of the replay buffer which reduces by almost a factor two the memory used,\n        at a cost of more complexity.\n        See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195\n        and https://github.com/DLR-RM/stable-baselines3/pull/28#issuecomment-637559274\n        Cannot be used in combination with handle_timeout_termination.\n    :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n        separately and treat the task as infinite horizon task.\n        https://github.com/DLR-RM/stable-baselines3/issues/284\n    ", "__init__": "<function ReplayBuffer.__init__ at 0x1338d0040>", "add": "<function ReplayBuffer.add at 0x1338d0180>", "sample": "<function ReplayBuffer.sample at 0x1338d0220>", "_get_samples": "<function ReplayBuffer._get_samples at 0x1338d02c0>", "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x1338d0360>)>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x1338bbd00>"}, "replay_buffer_kwargs": {}, "train_freq": {":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>", ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"}, "use_sde_at_warmup": false, "target_entropy": -8.0, "ent_coef": "auto", "target_update_interval": 1, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "batch_norm_stats": [], "batch_norm_stats_target": [], "system_info": {"OS": "macOS-14.4.1-arm64-arm-64bit Darwin Kernel Version 23.4.0: Fri Mar 15 00:12:41 PDT 2024; root:xnu-10063.101.17~1/RELEASE_ARM64_T8103", "Python": "3.12.3", "Stable-Baselines3": "2.3.2", "PyTorch": "2.3.1", "GPU Enabled": "False", "Numpy": "1.26.4", "Cloudpickle": "3.0.0", "Gymnasium": "0.29.1"}}
+{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnNhYy5wb2xpY2llc5SMCVNBQ1BvbGljeZSTlC4=", "__module__": "stable_baselines3.sac.policies", "__annotations__": "{'actor': <class 'stable_baselines3.sac.policies.Actor'>, 'critic': <class 'stable_baselines3.common.policies.ContinuousCritic'>, 'critic_target': <class 'stable_baselines3.common.policies.ContinuousCritic'>}", "__doc__": "\n    Policy class (with both actor and critic) for SAC.\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` when using gSDE to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param clip_mean: Clip the mean output when using gSDE to avoid numerical instability.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    :param n_critics: Number of critic networks to create.\n    :param share_features_extractor: Whether to share or not the features extractor\n        between the actor and the critic (this saves computation time)\n    ", "__init__": "<function SACPolicy.__init__ at 0x11f55f240>", "_build": "<function SACPolicy._build at 0x11f55f880>", "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x11f55f920>", "reset_noise": "<function SACPolicy.reset_noise at 0x11f55f9c0>", "make_actor": "<function SACPolicy.make_actor at 0x11f55fa60>", "make_critic": "<function SACPolicy.make_critic at 0x11f55fb00>", "forward": "<function SACPolicy.forward at 0x11f55fba0>", "_predict": "<function SACPolicy._predict at 0x11f55fc40>", "set_training_mode": "<function SACPolicy.set_training_mode at 0x11f55fce0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x11f5786c0>"}, "verbose": 0, "policy_kwargs": {"use_sde": false}, "num_timesteps": 975000, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1718033158578114641, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVTQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJbYAAAAAAAAAIsIIRAUDOE/O7C9Q7BR7j/VNfthvbSyPzyXVpvJ7bO/lpQiAKhL0z8D18h+CUbhvxWlo6uMvOA/FIRu+MXL4L9fhnvbErfgvw6xZ2dVQ+E/sqde5gWw4L8hLofHoszgv9uqvWEFs+A/JCVXXeTsFUDdwjvn5+P1P8hct10pWOa//2kCer+n/b8JnopGCvLxPyWcLDIYsPC/uF7qCg8W4D9GEfMuy6mKP/SL0A8F93e/JCaiknEVeT/Ov4LgNiv0v2rmR+LxdHG/VCNSBpANiz/RP4Nzf3gEwJSMBW51bXB5lIwFZHR5cGWUk5SMAmY4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsbhpSMAUOUdJRSlC4="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVTQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJbYAAAAAAAAANdz/rVocOI/TCP9PzEW7j8JmtfHbs20P4sWpj/mDrG/CxKqlxu81D9eKqDgtlThv4mBY4Niq+A/dMjM7ZfI4L9z2UeORLvgv6DD+Gup8Nw/YcnKGpOt4L8+dx06QNTgvzeSjp0Xa+M/kHYDb5KfFUCuHXM4YeDtP/KzQtAV7+i/8NEW4/beir8QOUIqevntv2a6GaOEVOm/uol/bG0OBcBWN6ttO4O2P3skrpSJfWQ/MQYHE87JUz/0yZSSF2kVQHhwoXjkjhm/QtJBbSrCUD85fNoChIXGv5SMBW51bXB5lIwFZHR5cGWUk5SMAmY4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsbhpSMAUOUdJRSlC4="}, "_episode_num": 1206, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.02500100000000005, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 964999, "buffer_size": 1000000, "batch_size": 256, "learning_starts": 10000, "tau": 0.005, "gamma": 0.99, "gradient_steps": 1, "optimize_memory_usage": false, "replay_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==", "__module__": "stable_baselines3.common.buffers", "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'next_observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'dones': <class 'numpy.ndarray'>, 'timeouts': <class 'numpy.ndarray'>}", "__doc__": "\n    Replay buffer used in off-policy algorithms like SAC/TD3.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param device: PyTorch device\n    :param n_envs: Number of parallel environments\n    :param optimize_memory_usage: Enable a memory efficient variant\n        of the replay buffer which reduces by almost a factor two the memory used,\n        at a cost of more complexity.\n        See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195\n        and https://github.com/DLR-RM/stable-baselines3/pull/28#issuecomment-637559274\n        Cannot be used in combination with handle_timeout_termination.\n    :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n        separately and treat the task as infinite horizon task.\n        https://github.com/DLR-RM/stable-baselines3/issues/284\n    ", "__init__": "<function ReplayBuffer.__init__ at 0x11f4d80e0>", "add": "<function ReplayBuffer.add at 0x11f4d8220>", "sample": "<function ReplayBuffer.sample at 0x11f4d82c0>", "_get_samples": "<function ReplayBuffer._get_samples at 0x11f4d8360>", "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x11f4d8400>)>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x11f4ccf80>"}, "replay_buffer_kwargs": {}, "train_freq": {":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>", ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"}, "use_sde_at_warmup": false, "target_entropy": -8.0, "ent_coef": "auto", "target_update_interval": 1, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float64", "bounded_below": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False]", "bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False]", "_shape": [27], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf]", "low_repr": "-inf", "high_repr": "inf", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "_shape": [8], "low": "[-1. -1. -1. -1. -1. -1. -1. -1.]", "high": "[1. 1. 1. 1. 1. 1. 1. 1.]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": "Generator(PCG64)"}, "n_envs": 1, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "batch_norm_stats": [], "batch_norm_stats_target": [], "system_info": {"OS": "macOS-14.4.1-arm64-arm-64bit Darwin Kernel Version 23.4.0: Fri Mar 15 00:12:41 PDT 2024; root:xnu-10063.101.17~1/RELEASE_ARM64_T8103", "Python": "3.12.3", "Stable-Baselines3": "2.3.2", "PyTorch": "2.3.1", "GPU Enabled": "False", "Numpy": "1.26.4", "Cloudpickle": "3.0.0", "Gymnasium": "0.29.1"}}

results.json

@@ -1 +1 @@
-{"mean_reward": 986.6937203000001, "std_reward": 0.9212612121860967, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-10T11:54:37.877627"}
+{"mean_reward": 4867.7374702, "std_reward": 1756.0175745657139, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-10T12:04:12.665007"}