Properly Trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -675.57 +/- 245.79
+      value: 287.18 +/- 26.44
       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 sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\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 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 0x7fac213b69d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fac213b6a60>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fac213b6af0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fac213b6b80>", "_build": "<function ActorCriticPolicy._build at 0x7fac213b6c10>", "forward": "<function ActorCriticPolicy.forward at 0x7fac213b6ca0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fac213b6d30>", "_predict": "<function ActorCriticPolicy._predict at 0x7fac213b6dc0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fac213b6e50>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fac213b6ee0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fac213b6f70>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fac213ae9f0>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_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": 16, "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": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu116", "GPU Enabled": "True", "Numpy": "1.21.6", "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 sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\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 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 0x7fac213b69d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fac213b6a60>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fac213b6af0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fac213b6b80>", "_build": "<function ActorCriticPolicy._build at 0x7fac213b6c10>", "forward": "<function ActorCriticPolicy.forward at 0x7fac213b6ca0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fac213b6d30>", "_predict": "<function ActorCriticPolicy._predict at 0x7fac213b6dc0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fac213b6e50>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fac213b6ee0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fac213b6f70>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fac213ae9f0>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_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": 16, "num_timesteps": 10010624, "_total_timesteps": 10000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1670906504954643471, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.0010623999999999079, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 2444, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu116", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0156bf28a365007f05fdf3c74ed8855a3f2d75bff74808cb1cbff8c292cfe35
-size 52863
+oid sha256:e724cdac9b99623c91de08b4dbcb7be12b1f58ba4c07cd4c5877dccffb2ac6d7
+size 147222

ppo-LunarLander-v2/data

@@ -42,28 +42,40 @@
         "_np_random": null
     },
     "n_envs": 16,
-    "num_timesteps": 0,
-    "_total_timesteps": 0,
+    "num_timesteps": 10010624,
+    "_total_timesteps": 10000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": null,
+    "start_time": 1670906504954643471,
     "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_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "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"
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
+    },
     "_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": -0.0010623999999999079,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 2444,
     "n_steps": 1024,
     "gamma": 0.999,
     "gae_lambda": 0.98,

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2497affac19a461e040f7a57c9a5933e93b10b5579b0a3d91d7d3978070520ec
-size 687
+oid sha256:db1d8c84f46fd4eff2d1f2d1506c75a048bc966228c6ad9235fe140c642c81ca
+size 88057

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25e3bc91a35dfa489905abb8611cbb36eb6435fc5e7e6bfc3aef0979896dd1c9
+oid sha256:93b089fe91bfd375086ce5d1556bb75a0f0213c64cf93c02aad4bbc472ede651
 size 43201

results.json

@@ -1 +1 @@
-{"mean_reward": -675.5694176646481, "std_reward": 245.78706608890474, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-13T06:50:17.053303"}
+{"mean_reward": 287.18253425061664, "std_reward": 26.4408226580204, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-13T06:55:34.733299"}