Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -6.96 +/- 2.11
+      value: -0.21 +/- 0.13
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92d42a5968944f248c361ca52f72012f964c358b6225699518f80a90d2ff1214
-size 59035
+oid sha256:f9a3e61e7f82e80d38125004a4a54d4a0249058939bc0f1cacbc70547cd1e569
+size 110788

a2c-PandaReachDense-v3/data

@@ -4,9 +4,9 @@
         ":serialized:": "gAWVRQAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMG011bHRpSW5wdXRBY3RvckNyaXRpY1BvbGljeZSTlC4=",
         "__module__": "stable_baselines3.common.policies",
         "__doc__": "\n    MultiInputActorClass policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\n\n    :param observation_space: Observation space (Tuple)\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 ortho_init: Whether to use or not orthogonal initialization\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 full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` 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 squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\n    :param features_extractor_class: Uses the CombinedExtractor\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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    ",
-        "__init__": "<function MultiInputActorCriticPolicy.__init__ at 0x756b67b3e170>",
+        "__init__": "<function MultiInputActorCriticPolicy.__init__ at 0x73687153a170>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x756b67b44c00>"
+        "_abc_impl": "<_abc._abc_data object at 0x736871540f40>"
     },
     "verbose": 1,
     "policy_kwargs": {
@@ -19,25 +19,46 @@
             "weight_decay": 0
         }
     },
-    "num_timesteps": 0,
-    "_total_timesteps": 0,
+    "num_timesteps": 2000000,
+    "_total_timesteps": 2000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 0.0,
+    "start_time": 1719415468298298466,
     "learning_rate": 0.0007,
     "tensorboard_log": null,
-    "_last_obs": null,
-    "_last_episode_starts": null,
-    "_last_original_obs": null,
+    "_last_obs": {
+        ":type:": "<class 'collections.OrderedDict'>",
+        ":serialized:": "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",
+        "achieved_goal": "[[ 0.26202804  0.92938524 -1.2344959 ]\n [-1.437279   -0.00588931  0.6530094 ]\n [ 0.3135787  -0.0177897   0.45883352]\n [ 0.3135787  -0.0177897   0.45883352]]",
+        "desired_goal": "[[ 0.21006571  0.3278273  -1.5266856 ]\n [-1.0980784   0.14411907  0.5362284 ]\n [-1.4764968  -0.5782032   0.8091961 ]\n [ 0.8743444   1.5609388   0.86127996]]",
+        "observation": "[[ 2.6202804e-01  9.2938524e-01 -1.2344959e+00 -1.6884769e-01\n  -3.1670950e-02 -1.3880404e+00]\n [-1.4372790e+00 -5.8893124e-03  6.5300941e-01 -7.6302272e-01\n   1.5150152e+00  1.5337125e+00]\n [ 3.1357870e-01 -1.7789701e-02  4.5883352e-01  4.6635371e-01\n  -1.6120772e-04  3.8074920e-01]\n [ 3.1357870e-01 -1.7789701e-02  4.5883352e-01  4.6635371e-01\n  -1.6120772e-04  3.8074920e-01]]"
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAQGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'collections.OrderedDict'>",
+        ":serialized:": "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",
+        "achieved_goal": "[[ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]]",
+        "desired_goal": "[[ 0.03509272 -0.1073987   0.14211239]\n [-0.1117898   0.1285752   0.06644592]\n [-0.06767353  0.1212405   0.25003725]\n [-0.05368968  0.10642055  0.2700862 ]]",
+        "observation": "[[ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]]"
+    },
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": 1.0,
+    "_current_progress_remaining": 0.0,
     "_stats_window_size": 100,
-    "ep_info_buffer": null,
-    "ep_success_buffer": null,
-    "_n_updates": 0,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVhgAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIhlLg=="
+    },
+    "_n_updates": 100000,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.dict.Dict'>",
         ":serialized:": "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",
@@ -74,13 +95,13 @@
         "__module__": "stable_baselines3.common.buffers",
         "__annotations__": "{'observation_space': <class 'gymnasium.spaces.dict.Dict'>, 'obs_shape': typing.Dict[str, typing.Tuple[int, ...]], 'observations': typing.Dict[str, numpy.ndarray]}",
         "__doc__": "\n    Dict Rollout buffer used in on-policy algorithms like A2C/PPO.\n    Extends the RolloutBuffer to use dictionary observations\n\n    It corresponds to ``buffer_size`` transitions collected\n    using the current policy.\n    This experience will be discarded after the policy update.\n    In order to use PPO objective, we also store the current value of each state\n    and the log probability of each taken action.\n\n    The term rollout here refers to the model-free notion and should not\n    be used with the concept of rollout used in model-based RL or planning.\n    Hence, it is only involved in policy and value function training but not action selection.\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 gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n        Equivalent to Monte-Carlo advantage estimate when set to 1.\n    :param gamma: Discount factor\n    :param n_envs: Number of parallel environments\n    ",
-        "__init__": "<function DictRolloutBuffer.__init__ at 0x756b67cf15a0>",
-        "reset": "<function DictRolloutBuffer.reset at 0x756b67cf1630>",
-        "add": "<function DictRolloutBuffer.add at 0x756b67cf16c0>",
-        "get": "<function DictRolloutBuffer.get at 0x756b67cf1750>",
-        "_get_samples": "<function DictRolloutBuffer._get_samples at 0x756b67cf17e0>",
+        "__init__": "<function DictRolloutBuffer.__init__ at 0x7368716ed5a0>",
+        "reset": "<function DictRolloutBuffer.reset at 0x7368716ed630>",
+        "add": "<function DictRolloutBuffer.add at 0x7368716ed6c0>",
+        "get": "<function DictRolloutBuffer.get at 0x7368716ed750>",
+        "_get_samples": "<function DictRolloutBuffer._get_samples at 0x7368716ed7e0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x756b67ceb9c0>"
+        "_abc_impl": "<_abc._abc_data object at 0x7368716e7c00>"
     },
     "rollout_buffer_kwargs": {},
     "normalize_advantage": false,

a2c-PandaReachDense-v3/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc0758cfb38edd34b7a3ca368ba5d9c919956bca5573ae6335d0be738127e637
-size 1120
+oid sha256:1e5eccc1cc00ff7bd8292e3c753189390e33bd39b4b3100f815ad470399c248e
+size 45167

a2c-PandaReachDense-v3/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61c0f7c42233cf87d4a59229f6f0b1a006b23ef9303b46eeb8bfd33744b98b3d
+oid sha256:705a69aeaf342a975087802b9083097783e0b646556f222bffc7516c455fbde0
 size 46447

config.json

@@ -1 +1 @@
-{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVRQAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMG011bHRpSW5wdXRBY3RvckNyaXRpY1BvbGljeZSTlC4=", "__module__": "stable_baselines3.common.policies", "__doc__": "\n    MultiInputActorClass policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\n\n    :param observation_space: Observation space (Tuple)\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 ortho_init: Whether to use or not orthogonal initialization\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 full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` 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 squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\n    :param features_extractor_class: Uses the CombinedExtractor\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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    ", "__init__": "<function MultiInputActorCriticPolicy.__init__ at 0x756b67b3e170>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x756b67b44c00>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVgQAAAAAAAAB9lCiMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/vrhR64UeujANlcHOURz7k+LWI42jxjAx3ZWlnaHRfZGVjYXmUSwB1dS4=", "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>", "optimizer_kwargs": {"alpha": 0.99, "eps": 1e-05, "weight_decay": 0}}, "num_timesteps": 0, "_total_timesteps": 0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 0.0, "learning_rate": 0.0007, "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.dict.Dict'>", ":serialized:": "gAWVsAMAAAAAAACMFWd5bW5hc2l1bS5zcGFjZXMuZGljdJSMBERpY3SUk5QpgZR9lCiMBnNwYWNlc5SMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwUZ3ltbmFzaXVtLnNwYWNlcy5ib3iUjANCb3iUk5QpgZR9lCiMBWR0eXBllIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowNYm91bmRlZF9iZWxvd5SMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYDAAAAAAAAAAEBAZRoE4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksDhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoHCiWAwAAAAAAAAABAQGUaCBLA4WUaCR0lFKUjAZfc2hhcGWUSwOFlIwDbG93lGgcKJYMAAAAAAAAAAAAIMEAACDBAAAgwZRoFksDhZRoJHSUUpSMBGhpZ2iUaBwolgwAAAAAAAAAAAAgQQAAIEEAACBBlGgWSwOFlGgkdJRSlIwIbG93X3JlcHKUjAUtMTAuMJSMCWhpZ2hfcmVwcpSMBDEwLjCUjApfbnBfcmFuZG9tlE51YowMZGVzaXJlZF9nb2FslGgNKYGUfZQoaBBoFmgZaBwolgMAAAAAAAAAAQEBlGggSwOFlGgkdJRSlGgnaBwolgMAAAAAAAAAAQEBlGggSwOFlGgkdJRSlGgsSwOFlGguaBwolgwAAAAAAAAAAAAgwQAAIMEAACDBlGgWSwOFlGgkdJRSlGgzaBwolgwAAAAAAAAAAAAgQQAAIEEAACBBlGgWSwOFlGgkdJRSlGg4jAUtMTAuMJRoOowEMTAuMJRoPE51YowLb2JzZXJ2YXRpb26UaA0pgZR9lChoEGgWaBloHCiWBgAAAAAAAAABAQEBAQGUaCBLBoWUaCR0lFKUaCdoHCiWBgAAAAAAAAABAQEBAQGUaCBLBoWUaCR0lFKUaCxLBoWUaC5oHCiWGAAAAAAAAAAAACDBAAAgwQAAIMEAACDBAAAgwQAAIMGUaBZLBoWUaCR0lFKUaDNoHCiWGAAAAAAAAAAAACBBAAAgQQAAIEEAACBBAAAgQQAAIEGUaBZLBoWUaCR0lFKUaDiMBS0xMC4wlGg6jAQxMC4wlGg8TnVidWgsTmgQTmg8TnViLg==", "spaces": "OrderedDict([('achieved_goal', Box(-10.0, 10.0, (3,), float32)), ('desired_goal', Box(-10.0, 10.0, (3,), float32)), ('observation', Box(-10.0, 10.0, (6,), float32))])", "_shape": null, "dtype": null, "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True]", "bounded_above": "[ True  True  True]", "_shape": [3], "low": "[-1. -1. -1.]", "high": "[1. 1. 1.]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": null}, "n_envs": 4, "n_steps": 5, "gamma": 0.99, "gae_lambda": 1.0, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "rollout_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOgAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwRRGljdFJvbGxvdXRCdWZmZXKUk5Qu", "__module__": "stable_baselines3.common.buffers", "__annotations__": "{'observation_space': <class 'gymnasium.spaces.dict.Dict'>, 'obs_shape': typing.Dict[str, typing.Tuple[int, ...]], 'observations': typing.Dict[str, numpy.ndarray]}", "__doc__": "\n    Dict Rollout buffer used in on-policy algorithms like A2C/PPO.\n    Extends the RolloutBuffer to use dictionary observations\n\n    It corresponds to ``buffer_size`` transitions collected\n    using the current policy.\n    This experience will be discarded after the policy update.\n    In order to use PPO objective, we also store the current value of each state\n    and the log probability of each taken action.\n\n    The term rollout here refers to the model-free notion and should not\n    be used with the concept of rollout used in model-based RL or planning.\n    Hence, it is only involved in policy and value function training but not action selection.\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 gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n        Equivalent to Monte-Carlo advantage estimate when set to 1.\n    :param gamma: Discount factor\n    :param n_envs: Number of parallel environments\n    ", "__init__": "<function DictRolloutBuffer.__init__ at 0x756b67cf15a0>", "reset": "<function DictRolloutBuffer.reset at 0x756b67cf1630>", "add": "<function DictRolloutBuffer.add at 0x756b67cf16c0>", "get": "<function DictRolloutBuffer.get at 0x756b67cf1750>", "_get_samples": "<function DictRolloutBuffer._get_samples at 0x756b67cf17e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x756b67ceb9c0>"}, "rollout_buffer_kwargs": {}, "normalize_advantage": false, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVswMAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLA0sTQwx0AIgAfACDAYMBUwCUToWUjAVmbG9hdJSFlIwScHJvZ3Jlc3NfcmVtYWluaW5nlIWUjGEvaG9tZS9tYXR0L2RvY3MvaG93VG8vYWkvdTYvaGYtZW52L2xpYi9weXRob24zLjEwL3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwIPGxhbWJkYT6US2FDAgwAlIwOdmFsdWVfc2NoZWR1bGWUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxhL2hvbWUvbWF0dC9kb2NzL2hvd1RvL2FpL3U2L2hmLWVudi9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlGgAjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoIX2UfZQoaBhoD4wMX19xdWFsbmFtZV9flIwhZ2V0X3NjaGVkdWxlX2ZuLjxsb2NhbHM+LjxsYW1iZGE+lIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoGYwHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlGgCKGgHKEsBSwBLAEsBSwFLE0MEiABTAJRoCSmMAV+UhZRoDowEZnVuY5RLhUMCBAGUjAN2YWyUhZQpdJRSlGgVTk5oHSlSlIWUdJRSlGgjaD19lH2UKGgYaDRoJowZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5RoKH2UaCpOaCtOaCxoGWgtTmguaDBHP0bwBo24useFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMIWUUpSFlGhFXZRoR32UdYaUhlIwLg=="}, "system_info": {"OS": "Linux-6.6.35-2-lts-x86_64-with-glibc2.39 # 1 SMP PREEMPT_DYNAMIC Fri, 21 Jun 2024 21:05:23 +0000", "Python": "3.10.12", "Stable-Baselines3": "2.3.2", "PyTorch": "2.3.1+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "Cloudpickle": "3.0.0", "Gymnasium": "0.29.1"}}
+{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVRQAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMG011bHRpSW5wdXRBY3RvckNyaXRpY1BvbGljeZSTlC4=", "__module__": "stable_baselines3.common.policies", "__doc__": "\n    MultiInputActorClass policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\n\n    :param observation_space: Observation space (Tuple)\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 ortho_init: Whether to use or not orthogonal initialization\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 full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` 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 squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\n    :param features_extractor_class: Uses the CombinedExtractor\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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    ", "__init__": "<function MultiInputActorCriticPolicy.__init__ at 0x73687153a170>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x736871540f40>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVgQAAAAAAAAB9lCiMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/vrhR64UeujANlcHOURz7k+LWI42jxjAx3ZWlnaHRfZGVjYXmUSwB1dS4=", "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>", "optimizer_kwargs": {"alpha": 0.99, "eps": 1e-05, "weight_decay": 0}}, "num_timesteps": 2000000, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1719415468298298466, "learning_rate": 0.0007, "tensorboard_log": null, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 0.26202804  0.92938524 -1.2344959 ]\n [-1.437279   -0.00588931  0.6530094 ]\n [ 0.3135787  -0.0177897   0.45883352]\n [ 0.3135787  -0.0177897   0.45883352]]", "desired_goal": "[[ 0.21006571  0.3278273  -1.5266856 ]\n [-1.0980784   0.14411907  0.5362284 ]\n [-1.4764968  -0.5782032   0.8091961 ]\n [ 0.8743444   1.5609388   0.86127996]]", "observation": "[[ 2.6202804e-01  9.2938524e-01 -1.2344959e+00 -1.6884769e-01\n  -3.1670950e-02 -1.3880404e+00]\n [-1.4372790e+00 -5.8893124e-03  6.5300941e-01 -7.6302272e-01\n   1.5150152e+00  1.5337125e+00]\n [ 3.1357870e-01 -1.7789701e-02  4.5883352e-01  4.6635371e-01\n  -1.6120772e-04  3.8074920e-01]\n [ 3.1357870e-01 -1.7789701e-02  4.5883352e-01  4.6635371e-01\n  -1.6120772e-04  3.8074920e-01]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAQGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]]", "desired_goal": "[[ 0.03509272 -0.1073987   0.14211239]\n [-0.1117898   0.1285752   0.06644592]\n [-0.06767353  0.1212405   0.25003725]\n [-0.05368968  0.10642055  0.2700862 ]]", "observation": "[[ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]]"}, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.0, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWV4AsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHv8rwpe/pMYeMAWyUSwOMAXSUR0CczOxPfsNUdX2UKGgGR7/baQFLWZqmaAdLBGgIR0CczHU/wAlwdX2UKGgGR7/RpJPIn0CjaAdLA2gIR0CczDwjt5UtdX2UKGgGR7/XYKYzBRAKaAdLBGgIR0CczLaJhvzfdX2UKGgGR7/LvS+g13t8aAdLA2gIR0CczH9Oh0yQdX2UKGgGR7/ZBnzxwyZbaAdLBGgIR0CczPm/336AdX2UKGgGR7/T79Q40dilaAdLA2gIR0CczEZVGTcJdX2UKGgGR7/Xs9B8hLXdaAdLBGgIR0CczMWd3B55dX2UKGgGR7/OREnb7CSBaAdLA2gIR0CczIr2QGOddX2UKGgGR7/BxBE8aGYbaAdLAmgIR0CczE7WuoxYdX2UKGgGR7+NxQzk6tDEaAdLAWgIR0CczFI2wV0tdX2UKGgGR7/bzqbBoEjgaAdLBGgIR0CczQjvd/KAdX2UKGgGR7/DDUExIre7aAdLAmgIR0CczJHe7+UAdX2UKGgGR7+hGSZBsyi3aAdLAWgIR0CczFW2w3YMdX2UKGgGR7/d6Ae7tiQUaAdLBGgIR0CczNUY8+zMdX2UKGgGR7+5W+49X9zfaAdLAmgIR0CczF4agmJFdX2UKGgGR7/QQGfPHDJmaAdLA2gIR0CczRTSsr/bdX2UKGgGR7/MNd7fHggpaAdLA2gIR0CczJ26ClJpdX2UKGgGR7/DQ8fV7Qb/aAdLAmgIR0CczGSi/O+qdX2UKGgGR7/EhXbM5fdAaAdLAmgIR0CczRtYSxqxdX2UKGgGR7/Wkl/pdKNAaAdLBWgIR0CczOcyFfzCdX2UKGgGR7/Pdhy8zyjIaAdLA2gIR0CczHAzHjp+dX2UKGgGR7+faDf3vhIfaAdLAWgIR0CczOqgAZKndX2UKGgGR7/YAE+xGDtgaAdLBWgIR0CczLAEMb3odX2UKGgGR7+i57PY4ACGaAdLAWgIR0CczHPf8/D+dX2UKGgGR7/bevpyIYWMaAdLBGgIR0CczSqW1MM7dX2UKGgGR7/CEOAiFCb+aAdLAmgIR0CczPFXq7iAdX2UKGgGR7+/Ai3XqZ+haAdLAmgIR0CczLazNUwSdX2UKGgGR7/Fsk6cRUWEaAdLAmgIR0CczHqPOpsHdX2UKGgGR7/IkKu0TlDGaAdLA2gIR0CczTan752ydX2UKGgGR7+0kNWluWKNaAdLAmgIR0CczPp1A7gbdX2UKGgGR7+7qSowVTJhaAdLAmgIR0CczL+2E0zkdX2UKGgGR7/I7qY7aIvbaAdLA2gIR0CczIa7EpAldX2UKGgGR7++lj3Ehq0uaAdLAmgIR0CczT12JSBLdX2UKGgGR7+fgFX7tRekaAdLAWgIR0CczUCb+cYqdX2UKGgGR7/KvpQk5ZKWaAdLA2gIR0CczQRigCfZdX2UKGgGR7/Vprk8zQ/paAdLBGgIR0CczMy0a6z3dX2UKGgGR7/HOJLuhK15aAdLA2gIR0CczJDBuXNUdX2UKGgGR7/Pw2ETQE6laAdLA2gIR0CczUyNGViXdX2UKGgGR7/PLzwtrbg1aAdLA2gIR0CczRBP9DQadX2UKGgGR7/QF6AvtdAxaAdLA2gIR0CczNi4J/oadX2UKGgGR7/U0btJFspHaAdLA2gIR0CczJyZKFqSdX2UKGgGR7/QkbPyCnP3aAdLA2gIR0CczVaFmFrVdX2UKGgGR7/OlwcYIjW1aAdLA2gIR0CczRpVjqfOdX2UKGgGR7/HS5RTCLuQaAdLA2gIR0CczOSofjjrdX2UKGgGR7/MqsEJSiudaAdLA2gIR0CczKiCaqjrdX2UKGgGR7/BHXmNipeeaAdLAmgIR0CczV9AX2ugdX2UKGgGR7/HrdnCfpUxaAdLA2gIR0CczSYJVsDXdX2UKGgGR7/Okk8ifQKKaAdLA2gIR0CczO5imVJMdX2UKGgGR7/TmV7hNucdaAdLA2gIR0CczLJDVpbmdX2UKGgGR7/Q8IzFdcB2aAdLA2gIR0CczWkM1CPZdX2UKGgGR7/OUrTYukDZaAdLA2gIR0CczTH+6y0KdX2UKGgGR7/CT0QK8cuKaAdLAmgIR0CczPdK/VRUdX2UKGgGR7/ESeRPoFFEaAdLAmgIR0CczLstkFwDdX2UKGgGR7+itT1kDp1SaAdLAWgIR0CczL6dUbT+dX2UKGgGR7/Mtf5ULlV+aAdLA2gIR0CczXVU+9rXdX2UKGgGR7/SgIhQm/nGaAdLA2gIR0CczTw482aVdX2UKGgGR7/USdOIqLCOaAdLA2gIR0CczQF/x2B8dX2UKGgGR7/Qr7O3UhFFaAdLA2gIR0CczYEtdzGQdX2UKGgGR7/DzYmLLpzLaAdLAmgIR0CczUT/Q0GedX2UKGgGR7+5B9kSVW0aaAdLAmgIR0CczQo8p1A8dX2UKGgGR7/dMl1KXfIkaAdLBGgIR0CczM4ZuQ6qdX2UKGgGR7+RzV+Zw4sFaAdLAWgIR0CczUiYsunNdX2UKGgGR7+9WS2Yv38GaAdLAmgIR0CczRFBY3efdX2UKGgGR7/XSofjjrAyaAdLA2gIR0CczYuxrzoVdX2UKGgGR7/YX531SOzZaAdLA2gIR0CczNhOP/70dX2UKGgGR7+lTefqX4TLaAdLAWgIR0CczY8twrDqdX2UKGgGR7/UjS5RTCLuaAdLA2gIR0CczVL0Bfa6dX2UKGgGR7+9AAyVObiIaAdLAmgIR0CczRhF3IMjdX2UKGgGR7/Oclw97ngYaAdLA2gIR0CczOQmNR3vdX2UKGgGR7/S+H8CPp6haAdLA2gIR0CczSO8TSLJdX2UKGgGR7/UXAuZkTYeaAdLBGgIR0CczZ4jrzGxdX2UKGgGR7/efCyhSLqEaAdLBGgIR0CczWITGo73dX2UKGgGR7/JYhdMTN+taAdLA2gIR0CczO5I6KcedX2UKGgGR7/LKcurZJ05aAdLA2gIR0CczS/JeVs2dX2UKGgGR7/FgzguRLbpaAdLA2gIR0CczapCKJl8dX2UKGgGR7/WIT4+KTB7aAdLBGgIR0CczXEvTPSldX2UKGgGR7/KW9lEqlP8aAdLA2gIR0CczPpCKJl8dX2UKGgGR7/MSIxgy/KyaAdLA2gIR0CczbQv6CUYdX2UKGgGR7/LAqur6tT2aAdLA2gIR0CczXzl90A+dX2UKGgGR7/Hy7PIGQjmaAdLA2gIR0CczQXj2i+MdX2UKGgGR7/f/Ue+23KCaAdLBmgIR0CczUVrAP/adX2UKGgGR7/RQOFxn3+NaAdLA2gIR0Cczb/sVtXQdX2UKGgGR7/J2KVII4VAaAdLA2gIR0CczYbHZK4AdX2UKGgGR7/AQxvegte2aAdLAmgIR0CczUwQUYbbdX2UKGgGR7/Kq94/u9eyaAdLA2gIR0CczRABT4tZdX2UKGgGR7/P22Xsw+MZaAdLA2gIR0Cczcu4gA6udX2UKGgGR7+z3pOerdWRaAdLAmgIR0CczY+RYA80dX2UKGgGR7/JXoTwlSjyaAdLA2gIR0CczRunMt9QdX2UKGgGR7+4dELH+6y0aAdLAmgIR0CczdJoCdSVdX2UKGgGR7/b1RtP557gaAdLBGgIR0CczZyhSLqEdX2UKGgGR7/SmXPZ7HAAaAdLA2gIR0CczSXaakRBdX2UKGgGR7/R8CPp6hQFaAdLA2gIR0Cczd64Ds+ndX2UKGgGR7/bJng5zYEoaAdLB2gIR0CczWel9BrvdX2UKGgGR7/DUxVQyhzvaAdLAmgIR0CczS5yU9pzdX2UKGgGR7/EMYuTRplCaAdLAmgIR0CczeUj9n9OdX2UKGgGR7/F544ZMtbtaAdLA2gIR0Cczajmjj7zdX2UKGgGR7+5m5Dqnm7raAdLAmgIR0CczW4fOlfrdX2UKGgGR7/EFJQLux8laAdLAmgIR0CczXRQaaTfdX2UKGgGR7/KBaLXL/0eaAdLA2gIR0CczTg4wRGudWUu"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVhgAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIhlLg=="}, "_n_updates": 100000, "observation_space": {":type:": "<class 'gymnasium.spaces.dict.Dict'>", ":serialized:": "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", "spaces": "OrderedDict([('achieved_goal', Box(-10.0, 10.0, (3,), float32)), ('desired_goal', Box(-10.0, 10.0, (3,), float32)), ('observation', Box(-10.0, 10.0, (6,), float32))])", "_shape": null, "dtype": null, "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True]", "bounded_above": "[ True  True  True]", "_shape": [3], "low": "[-1. -1. -1.]", "high": "[1. 1. 1.]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": null}, "n_envs": 4, "n_steps": 5, "gamma": 0.99, "gae_lambda": 1.0, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "rollout_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOgAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwRRGljdFJvbGxvdXRCdWZmZXKUk5Qu", "__module__": "stable_baselines3.common.buffers", "__annotations__": "{'observation_space': <class 'gymnasium.spaces.dict.Dict'>, 'obs_shape': typing.Dict[str, typing.Tuple[int, ...]], 'observations': typing.Dict[str, numpy.ndarray]}", "__doc__": "\n    Dict Rollout buffer used in on-policy algorithms like A2C/PPO.\n    Extends the RolloutBuffer to use dictionary observations\n\n    It corresponds to ``buffer_size`` transitions collected\n    using the current policy.\n    This experience will be discarded after the policy update.\n    In order to use PPO objective, we also store the current value of each state\n    and the log probability of each taken action.\n\n    The term rollout here refers to the model-free notion and should not\n    be used with the concept of rollout used in model-based RL or planning.\n    Hence, it is only involved in policy and value function training but not action selection.\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 gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n        Equivalent to Monte-Carlo advantage estimate when set to 1.\n    :param gamma: Discount factor\n    :param n_envs: Number of parallel environments\n    ", "__init__": "<function DictRolloutBuffer.__init__ at 0x7368716ed5a0>", "reset": "<function DictRolloutBuffer.reset at 0x7368716ed630>", "add": "<function DictRolloutBuffer.add at 0x7368716ed6c0>", "get": "<function DictRolloutBuffer.get at 0x7368716ed750>", "_get_samples": "<function DictRolloutBuffer._get_samples at 0x7368716ed7e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7368716e7c00>"}, "rollout_buffer_kwargs": {}, "normalize_advantage": false, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.6.35-2-lts-x86_64-with-glibc2.39 # 1 SMP PREEMPT_DYNAMIC Fri, 21 Jun 2024 21:05:23 +0000", "Python": "3.10.12", "Stable-Baselines3": "2.3.2", "PyTorch": "2.3.1+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "Cloudpickle": "3.0.0", "Gymnasium": "0.29.1"}}

results.json

@@ -1 +1 @@
-{"mean_reward": -6.96462598592043, "std_reward": 2.1112283997180477, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-26T12:14:40.667126"}
+{"mean_reward": -0.21209091152995824, "std_reward": 0.13088502713238226, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-26T12:55:10.790118"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cff09e9f475ab427526bc67bd68c14dc7e1d29ae46e013d05c9b3c52496bd1c
+oid sha256:fc6e4a7042ce968ffbfa812584ccf70be6e03f0d5eb3eab5f65062ffcd1fa54f
 size 2646