Smaller number of steps, fifth attempt

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 278.09 +/- 16.09
+      value: 294.19 +/- 21.02
       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 0x12f83c790>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x12f83c820>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x12f83c8b0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x12f83c940>", "_build": "<function ActorCriticPolicy._build at 0x12f83c9d0>", "forward": "<function ActorCriticPolicy.forward at 0x12f83ca60>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x12f83caf0>", "_predict": "<function ActorCriticPolicy._predict at 0x12f83cb80>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x12f83cc10>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x12f83cca0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x12f83cd30>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x12f83d380>"}, "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": 2007040, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1651738328.985027, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAObSAr2kcFW5h7I6OIlsnrB953a7NuJdtwAAgD8AAIA/mitmvY+4Fz0Ybvc9JTdMvpM4P71IdZ49AAAAAAAAAAANP2Q+s0+RP+KwFj+n9yi/9l3XPllqjz4AAAAAAAAAAJrIIz2O9qC8Bst+vocwBzsJtZ89KqHtPQAAgD8AAIA/zSTWO0PZUbwoark+jhXgvWFx5LzU0sO+AACAPwAAgD8AZ349RL63PuEKOr7cDxy/oBhOPEoL470AAAAAAAAAAACMhzyPyk663dNptjF/27GytHg7vj2KNQAAgD8AAIA/ZtROPHlZVj4KKv+8AG/1vjBK6DsoyFK9AAAAAAAAAAAAdjm8KRhNutE0nLYiR+CxqLLKOtecuTUAAIA/AACAP2Y0B7wpiFK6njOdNXc92y7ENoY5Z+SwtAAAgD8AAIA/jr2BvhO+Ej/K+fK8xvUYvzgKxr7MnaM9AAAAAAAAAABmhj06CudcuYCaSLeZJviypxpQO/qjbjYAAIA/AACAPwBs/7v1YrI/2nGEvbPgT76Xfs88Cnk/PAAAAAAAAAAArSQJPoid5z61vr2861o4vwoQjT6qfI29AAAAAAAAAACArRU9emGRP1jk8D0Zi0a/7ezXPXOYJT4AAAAAAAAAAHPG+L2Egd09d1WPPu2ukb427DK9iMzTPQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="}, "_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": -0.0035199999999999676, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 2940, "n_steps": 512, "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": 12, "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 0x128cc3790>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x128cc3820>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x128cc38b0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x128cc3940>", "_build": "<function ActorCriticPolicy._build at 0x128cc39d0>", "forward": "<function ActorCriticPolicy.forward at 0x128cc3a60>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x128cc3af0>", "_predict": "<function ActorCriticPolicy._predict at 0x128cc3b80>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x128cc3c10>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x128cc3ca0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x128cc3d30>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x128b45a00>"}, "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": 2007040, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1651738328.985027, "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": -0.0035199999999999676, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 2940, "n_steps": 512, "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": 12, "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:e6ddea91304d3d25312c55392088e02bb961211f4d6cf6cafab3ef162534bbe6
+oid sha256:4e0cb2ef00703a7118f73a8c2cb724500dbbb4cd4afd3d03fd069f801322fe32
 size 143843

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 0x12f83c790>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x12f83c820>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x12f83c8b0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x12f83c940>",
-        "_build": "<function ActorCriticPolicy._build at 0x12f83c9d0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x12f83ca60>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x12f83caf0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x12f83cb80>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x12f83cc10>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x12f83cca0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x12f83cd30>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x128cc3790>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x128cc3820>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x128cc38b0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x128cc3940>",
+        "_build": "<function ActorCriticPolicy._build at 0x128cc39d0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x128cc3a60>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x128cc3af0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x128cc3b80>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x128cc3c10>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x128cc3ca0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x128cc3d30>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x12f83d380>"
+        "_abc_impl": "<_abc._abc_data object at 0x128b45a00>"
     },
     "verbose": 1,
     "policy_kwargs": {},

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c68e4133cfbc73e68a22dc88f02beff6baa66d63470eb2eaf8fb99b4a33e640b
-size 338287
+oid sha256:9a60edc05f4a5f5c630f0ba128da986ec3963f2b60f11a488e27a51b1dcd4cf1
+size 326830

results.json

@@ -1 +1 @@
-{"mean_reward": 278.08818740168124, "std_reward": 16.085586323815544, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-05T10:47:52.164695"}
+{"mean_reward": 294.18970941789087, "std_reward": 21.015080735568688, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-05T10:49:06.257697"}