Uploading the same model to see how random the evaluation is

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 282.13 +/- 17.54
+      value: 281.11 +/- 17.97
       name: mean_reward
     task:
       type: reinforcement-learning

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 0x1530fe790>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x1530fe820>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x1530fe8b0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x1530fe940>", "_build": "<function ActorCriticPolicy._build at 0x1530fe9d0>", "forward": "<function ActorCriticPolicy.forward at 0x1530fea60>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x1530feaf0>", "_predict": "<function ActorCriticPolicy._predict at 0x1530feb80>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x1530fec10>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x1530feca0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x1530fed30>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x1530ffa40>"}, "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:": "gAWViAAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 2015232, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1651733322.556105, "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": -0.007616000000000067, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 984, "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": 16, "n_epochs": 8, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "macOS-12.3.1-arm64-arm-64bit Darwin Kernel Version 21.4.0: Fri Mar 18 00:47:26 PDT 2022; root:xnu-8020.101.4~15/RELEASE_ARM64_T8101", "Python": "3.9.0", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0", "GPU Enabled": "False", "Numpy": "1.21.5", "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 0x14c3e7790>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x14c3e7820>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x14c3e78b0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x14c3e7940>", "_build": "<function ActorCriticPolicy._build at 0x14c3e79d0>", "forward": "<function ActorCriticPolicy.forward at 0x14c3e7a60>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x14c3e7af0>", "_predict": "<function ActorCriticPolicy._predict at 0x14c3e7b80>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x14c3e7c10>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x14c3e7ca0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x14c3e7d30>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x14bb94440>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "gAWVpQEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLCIWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAAAAAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/5RoC0sIhZSMAUOUdJRSlIwEaGlnaJRoEyiWIAAAAAAAAAAAAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAf5RoC0sIhZRoFnSUUpSMDWJvdW5kZWRfYmVsb3eUaBMolggAAAAAAAAAAAAAAAAAAACUaAiMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLCIWUaBZ0lFKUjA1ib3VuZGVkX2Fib3ZllGgTKJYIAAAAAAAAAAAAAAAAAAAAlGgiSwiFlGgWdJRSlIwKX25wX3JhbmRvbZROdWIu", "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:": "gAWViAAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 2015232, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1651733322.556105, "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": -0.007616000000000067, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 984, "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": 16, "n_epochs": 8, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "macOS-12.3.1-arm64-arm-64bit Darwin Kernel Version 21.4.0: Fri Mar 18 00:47:26 PDT 2022; root:xnu-8020.101.4~15/RELEASE_ARM64_T8101", "Python": "3.9.0", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0", "GPU Enabled": "False", "Numpy": "1.21.5", "Gym": "0.21.0"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84109fc858a4abf7b4a76048a2f9dba3b3de4e4b4e0efc84733c2bc5bc91c93b
+oid sha256:be3daece76f6376b658155f4dde8886cac963ca67380d2b857b8714fb546e367
 size 143845

ppo-LunarLander-v2/data

@@ -4,19 +4,19 @@
         ":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 0x1530fe790>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x1530fe820>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x1530fe8b0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x1530fe940>",
-        "_build": "<function ActorCriticPolicy._build at 0x1530fe9d0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x1530fea60>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x1530feaf0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x1530feb80>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x1530fec10>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x1530feca0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x1530fed30>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x14c3e7790>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x14c3e7820>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x14c3e78b0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x14c3e7940>",
+        "_build": "<function ActorCriticPolicy._build at 0x14c3e79d0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x14c3e7a60>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x14c3e7af0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x14c3e7b80>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x14c3e7c10>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x14c3e7ca0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x14c3e7d30>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x1530ffa40>"
+        "_abc_impl": "<_abc._abc_data object at 0x14bb94440>"
     },
     "verbose": 1,
     "policy_kwargs": {},

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b49bf8b9886c0797cd794ebfc851db92f43a5513083c0edc8fe260be43acdd00
-size 360448
+oid sha256:1749252ec1b54b4b62bffad4c9476966c661cf2c11915cc5a9a1fab95b1cd23f
+size 372014

results.json

@@ -1 +1 @@
-{"mean_reward": 282.12655971609234, "std_reward": 17.54225069771694, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-05T10:02:10.737128"}
+{"mean_reward": 281.11134498338237, "std_reward": 17.967991772265123, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-05T10:08:47.268388"}