Upload model to Hugging Face

PPO-default.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47bc773652a4bc87311692d42de5f3ffbadcb848a9c54148ef09b530457d515c
-size 50408
+oid sha256:694bc9da66a9c110e1769ab465686a62609eb3f1ca16ee3a18c91afee94f8b3e
+size 136519

PPO-default/data

@@ -4,20 +4,20 @@
         ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
         "__module__": "stable_baselines3.common.policies",
         "__doc__": "\n    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\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: Features extractor to use.\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 ActorCriticPolicy.__init__ at 0x7f4fb51730a0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f4fb5173130>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f4fb51731c0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f4fb5173250>",
-        "_build": "<function ActorCriticPolicy._build at 0x7f4fb51732e0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7f4fb5173370>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f4fb5173400>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f4fb5173490>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7f4fb5173520>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f4fb51735b0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f4fb5173640>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f4fb51736d0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7fc32e0313f0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc32e031480>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc32e031510>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc32e0315a0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fc32e031630>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fc32e0316c0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fc32e031750>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc32e0317e0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fc32e031870>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc32e031900>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc32e031990>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc32e031a20>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f4fb5263780>"
+        "_abc_impl": "<_abc._abc_data object at 0x7fc32e02e2c0>"
     },
     "verbose": true,
     "policy_kwargs": {},
@@ -43,28 +43,40 @@
         "_np_random": null
     },
     "n_envs": 4,
-    "num_timesteps": 0,
-    "_total_timesteps": 0,
+    "num_timesteps": 106496,
+    "_total_timesteps": 100000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": null,
+    "start_time": 1675306694226128954,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "lr_schedule": {
         ":type:": "<class 'function'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
+    },
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVpQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYwAAAAAAAAAAAAgD8AAIA/AACAPwAAgD8AAIA/AACAPwAAgD8AAIA/AACAPwAAgD8AAIA/AACAP5SMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLBEsDhpSMAUOUdJRSlC4="
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="
     },
-    "_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,
-    "ep_info_buffer": null,
-    "ep_success_buffer": null,
-    "_n_updates": 0,
+    "_current_progress_remaining": -0.0649599999999999,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 130,
     "n_steps": 2048,
     "gamma": 0.99,
     "gae_lambda": 0.95,
@@ -75,7 +87,7 @@
     "n_epochs": 10,
     "clip_range": {
         ":type:": "<class 'function'>",
-        ":serialized:": "gAWVCwMAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMbC9ob21lL25vaXNlYnJpZGdlL21pbmljb25kYTMvZW52cy9odWdnaW5nZmFjZS9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4JDAgQBlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMbC9ob21lL25vaXNlYnJpZGdlL21pbmljb25kYTMvZW52cy9odWdnaW5nZmFjZS9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/yZmZmZmZmoWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="
+        ":serialized:": "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"
     },
     "clip_range_vf": null,
     "normalize_advantage": true,

PPO-default/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2497affac19a461e040f7a57c9a5933e93b10b5579b0a3d91d7d3978070520ec
-size 687
+oid sha256:1eb704def2bf1af2dbbdcf723425e44b57b2d22ef94e347bd73830c533aa5912
+size 82809

PPO-default/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e31f0df4bf01e2e95d843265a766ad33eec38e91be4dd0fd0af8e358180c683e
-size 40705
+oid sha256:ebe9c9d20e43e92f597873495fcad3f78076222b0e2f94f59d5dcfbd156bb4ba
+size 40833

PPO-default/system_info.txt

@@ -1,7 +1,7 @@
-- OS: Linux-5.10.0-9-amd64-x86_64-with-glibc2.31 # 1 SMP Debian 5.10.70-1 (2021-09-30)
+- OS: Linux-5.15.0-58-generic-x86_64-with-glibc2.35 # 64-Ubuntu SMP Thu Jan 5 11:43:13 UTC 2023
 - Python: 3.10.9
 - Stable-Baselines3: 1.7.0
 - PyTorch: 1.13.1+cu117
-- GPU Enabled: False
+- GPU Enabled: True
 - Numpy: 1.24.1
 - Gym: 0.21.0

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Roomba
     metrics:
     - type: mean_reward
-      value: -56.10 +/- 36.43
+      value: 185.60 +/- 43.20
       name: mean_reward
       verified: false
 ---

config.json

@@ -1 +1 @@
-{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n    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\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: Features extractor to use.\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 ActorCriticPolicy.__init__ at 0x7f4fb51730a0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f4fb5173130>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f4fb51731c0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f4fb5173250>", "_build": "<function ActorCriticPolicy._build at 0x7f4fb51732e0>", "forward": "<function ActorCriticPolicy.forward at 0x7f4fb5173370>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f4fb5173400>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f4fb5173490>", "_predict": "<function ActorCriticPolicy._predict at 0x7f4fb5173520>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f4fb51735b0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f4fb5173640>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f4fb51736d0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f4fb5263780>"}, "verbose": true, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "gAWVbQEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLA4WUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWDAAAAAAAAAAAAAAAAAAAAAAAAACUaApLA4WUjAFDlHSUUpSMBGhpZ2iUaBIolgwAAAAAAAAAAACAPwAAgD8AAIA/lGgKSwOFlGgVdJRSlIwNYm91bmRlZF9iZWxvd5RoEiiWAwAAAAAAAAABAQGUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLA4WUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYDAAAAAAAAAAEBAZRoIUsDhZRoFXSUUpSMCl9ucF9yYW5kb22UTnViLg==", "dtype": "float32", "_shape": [3], "low": "[0. 0. 0.]", "high": "[1. 1. 1.]", "bounded_below": "[ True  True  True]", "bounded_above": "[ True  True  True]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 4, "num_timesteps": 0, "_total_timesteps": 0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": null, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_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, "ep_info_buffer": null, "ep_success_buffer": null, "_n_updates": 0, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.10.0-9-amd64-x86_64-with-glibc2.31 # 1 SMP Debian 5.10.70-1 (2021-09-30)", "Python": "3.10.9", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu117", "GPU Enabled": "False", "Numpy": "1.24.1", "Gym": "0.21.0"}}
+{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n    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\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: Features extractor to use.\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 ActorCriticPolicy.__init__ at 0x7fc32e0313f0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc32e031480>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc32e031510>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc32e0315a0>", "_build": "<function ActorCriticPolicy._build at 0x7fc32e031630>", "forward": "<function ActorCriticPolicy.forward at 0x7fc32e0316c0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fc32e031750>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc32e0317e0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fc32e031870>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc32e031900>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc32e031990>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc32e031a20>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fc32e02e2c0>"}, "verbose": true, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [3], "low": "[0. 0. 0.]", "high": "[1. 1. 1.]", "bounded_below": "[ True  True  True]", "bounded_above": "[ True  True  True]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 4, "num_timesteps": 106496, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1675306694226128954, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVpQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYwAAAAAAAAAAAAgD8AAIA/AACAPwAAgD8AAIA/AACAPwAAgD8AAIA/AACAPwAAgD8AAIA/AACAP5SMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLBEsDhpSMAUOUdJRSlC4="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.0649599999999999, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 130, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.15.0-58-generic-x86_64-with-glibc2.35 # 64-Ubuntu SMP Thu Jan 5 11:43:13 UTC 2023", "Python": "3.10.9", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu117", "GPU Enabled": "True", "Numpy": "1.24.1", "Gym": "0.21.0"}}

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57a0ba31f3e730e24b37384d6804a8718948234ccbc05cf03ffd0098191362d6
-size 732135
+oid sha256:cf0fbbf883bcbf4a5bad9c091b3195a2109a8a69ed9b2c6d9c369233d546ac01
+size 1164305

results.json

@@ -1 +1 @@
-{"mean_reward": -56.1, "std_reward": 36.43473617305332, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-31T08:05:05.734077"}
+{"mean_reward": 185.6, "std_reward": 43.2, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-01T19:00:21.981137"}