Test commit

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: -528.34 +/- 0.00
+      value: -574.85 +/- 0.00
       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 0x7fa037cb9430>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fa037cb94c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fa037cb9550>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fa037cb95e0>", "_build": "<function ActorCriticPolicy._build at 0x7fa037cb9670>", "forward": "<function ActorCriticPolicy.forward at 0x7fa037cb9700>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fa037cb9790>", "_predict": "<function ActorCriticPolicy._predict at 0x7fa037cb9820>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fa037cb98b0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fa037cb9940>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fa037cb99d0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fa037caeae0>"}, "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:": "gAWVgQAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwFc2hhcGWUKYwFZHR5cGWUjAVudW1weZRoB5OUjAJpOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRijApfbnBfcmFuZG9tlE51Yi4=", "n": 4, "shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "num_timesteps": 2048, "_total_timesteps": 10, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1657186802.1426473, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAAByCjwKxhw/mt6+vBn5pL87pR8+C0OVPQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -203.8, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 10, "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, "target_kl": null, "system_info": {"OS": "Linux-5.13.0-52-generic-x86_64-with-glibc2.17 #59~20.04.1-Ubuntu SMP Thu Jun 16 21:21:28 UTC 2022", "Python": "3.8.13", "Stable-Baselines3": "1.4.0", "PyTorch": "1.12.0+cu102", "GPU Enabled": "True", "Numpy": "1.23.0", "Gym": "0.19.0"}}
+{"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 0x7f11d093a430>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f11d093a4c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f11d093a550>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f11d093a5e0>", "_build": "<function ActorCriticPolicy._build at 0x7f11d093a670>", "forward": "<function ActorCriticPolicy.forward at 0x7f11d093a700>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f11d093a790>", "_predict": "<function ActorCriticPolicy._predict at 0x7f11d093a820>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f11d093a8b0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f11d093a940>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f11d093a9d0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f11d09a0ae0>"}, "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:": "gAWVgQAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwFc2hhcGWUKYwFZHR5cGWUjAVudW1weZRoB5OUjAJpOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRijApfbnBfcmFuZG9tlE51Yi4=", "n": 4, "shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "num_timesteps": 2048, "_total_timesteps": 10, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1657186946.8306313, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAEDzYr6I4Yg/ZBYOv55lML8Jo1k8Gb0DvgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -203.8, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 10, "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, "target_kl": null, "system_info": {"OS": "Linux-5.13.0-52-generic-x86_64-with-glibc2.17 #59~20.04.1-Ubuntu SMP Thu Jun 16 21:21:28 UTC 2022", "Python": "3.8.13", "Stable-Baselines3": "1.4.0", "PyTorch": "1.12.0+cu102", "GPU Enabled": "True", "Numpy": "1.23.0", "Gym": "0.19.0"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93e2f10a282f399342ed161e2e5f59a4eca08942262a36b793634bbae15de308
-size 141540
+oid sha256:cc316c0e96c0ec5d05ed484362a729a79d59ddf20cdfaf9a1c62b114c8c6ca21
+size 141380

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 0x7fa037cb9430>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fa037cb94c0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fa037cb9550>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fa037cb95e0>",
-        "_build": "<function ActorCriticPolicy._build at 0x7fa037cb9670>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7fa037cb9700>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fa037cb9790>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7fa037cb9820>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fa037cb98b0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fa037cb9940>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fa037cb99d0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f11d093a430>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f11d093a4c0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f11d093a550>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f11d093a5e0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f11d093a670>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f11d093a700>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f11d093a790>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f11d093a820>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f11d093a8b0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f11d093a940>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f11d093a9d0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x7fa037caeae0>"
+        "_abc_impl": "<_abc_data object at 0x7f11d09a0ae0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -47,7 +47,7 @@
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1657186802.1426473,
+    "start_time": 1657186946.8306313,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "lr_schedule": {
@@ -56,7 +56,7 @@
     },
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAAByCjwKxhw/mt6+vBn5pL87pR8+C0OVPQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAEDzYr6I4Yg/ZBYOv55lML8Jo1k8Gb0DvgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -69,7 +69,7 @@
     "_current_progress_remaining": -203.8,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f7f480b72ced97a9df8d86129333f1dbe50508ef85f7cdb76d6e0dadb7be024
+oid sha256:c5ed9bd50ed591c9e5db68e46060acc91589f4fd8bed71fd3e2f6390090d7bb0
 size 87545

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47afb04b8e9117e5327a6120032367f4c78b24d85fb0ff03dee14379d5143ca4
+oid sha256:02234945497dda3111f32a61085217ba5f881b4cc4304a01a7d869cf3fbcf8c1
 size 43073

results.json

@@ -1 +1 @@
-{"mean_reward": -528.339659, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 1, "eval_datetime": "2022-07-07T11:40:05.148455"}
+{"mean_reward": -574.845719, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 1, "eval_datetime": "2022-07-07T11:42:29.874169"}