3m training steps with linear learning rate scheduler

3m-linlr-ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f827b54d53b4ff485955d1930a9454e0a1d7f2409f31f9bcc7ed7b897ffa843
+oid sha256:474a9d027581268b0b3bdab0d2f38615cab56febc719f067384b2008bb97a372
 size 147358

3m-linlr-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 0x7f8a805f5f70>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f8a805fa040>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f8a805fa0d0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f8a805fa160>",
-        "_build": "<function ActorCriticPolicy._build at 0x7f8a805fa1f0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7f8a805fa280>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f8a805fa310>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7f8a805fa3a0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f8a805fa430>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f8a805fa4c0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f8a805fa550>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f6d701b5f70>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f6d701bb040>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f6d701bb0d0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f6d701bb160>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f6d701bb1f0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f6d701bb280>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f6d701bb310>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f6d701bb3a0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f6d701bb430>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f6d701bb4c0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f6d701bb550>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x7f8a805efd80>"
+        "_abc_impl": "<_abc_data object at 0x7f6d701afd80>"
     },
     "verbose": 1,
     "policy_kwargs": {},

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 229.47 +/- 95.01
+      value: 289.79 +/- 15.91
       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 0x7f8a805f5f70>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f8a805fa040>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f8a805fa0d0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f8a805fa160>", "_build": "<function ActorCriticPolicy._build at 0x7f8a805fa1f0>", "forward": "<function ActorCriticPolicy.forward at 0x7f8a805fa280>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f8a805fa310>", "_predict": "<function ActorCriticPolicy._predict at 0x7f8a805fa3a0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f8a805fa430>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f8a805fa4c0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f8a805fa550>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f8a805efd80>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "gAWVnwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLCIWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAAAAAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/5RoCksIhZSMAUOUdJRSlIwEaGlnaJRoEiiWIAAAAAAAAAAAAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAf5RoCksIhZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolggAAAAAAAAAAAAAAAAAAACUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLCIWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYIAAAAAAAAAAAAAAAAAAAAlGghSwiFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu", "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": 1, "num_timesteps": 3014656, "_total_timesteps": 3000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1671614346339791904, "learning_rate": {":type:": "<class 'function'>", ":serialized:": "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"}, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": null, "_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": -0.004885333333333408, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 736, "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-5.15.79.1-microsoft-standard-WSL2-x86_64-with-glibc2.29 #1 SMP Wed Nov 23 01:01:46 UTC 2022", "Python": "3.8.10", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.1+cu117", "GPU Enabled": "True", "Numpy": "1.23.5", "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 0x7f6d701b5f70>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f6d701bb040>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f6d701bb0d0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f6d701bb160>", "_build": "<function ActorCriticPolicy._build at 0x7f6d701bb1f0>", "forward": "<function ActorCriticPolicy.forward at 0x7f6d701bb280>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f6d701bb310>", "_predict": "<function ActorCriticPolicy._predict at 0x7f6d701bb3a0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f6d701bb430>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f6d701bb4c0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f6d701bb550>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f6d701afd80>"}, "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": 1, "num_timesteps": 3014656, "_total_timesteps": 3000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1671614346339791904, "learning_rate": {":type:": "<class 'function'>", ":serialized:": "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"}, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": null, "_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": -0.004885333333333408, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 736, "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-5.15.79.1-microsoft-standard-WSL2-x86_64-with-glibc2.29 #1 SMP Wed Nov 23 01:01:46 UTC 2022", "Python": "3.8.10", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.1+cu117", "GPU Enabled": "True", "Numpy": "1.23.5", "Gym": "0.21.0"}}

results.json

@@ -1 +1 @@
-{"mean_reward": 229.46675189999996, "std_reward": 95.01154926356209, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-21T11:26:44.315420"}
+{"mean_reward": 289.7889313, "std_reward": 15.905510942654882, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-21T11:28:04.899835"}