Test commit

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: -194.73 +/- 0.00
+      value: -247.76 +/- 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 0x7f63820c1430>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f63820c14c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f63820c1550>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f63820c15e0>", "_build": "<function ActorCriticPolicy._build at 0x7f63820c1670>", "forward": "<function ActorCriticPolicy.forward at 0x7f63820c1700>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f63820c1790>", "_predict": "<function ActorCriticPolicy._predict at 0x7f63820c1820>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f63820c18b0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f63820c1940>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f63820c19d0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f6382127ae0>"}, "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": 1657183283.7582548, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAHCkqD7QFDc/HbJGPyVlgb8AZPS+dnlEvgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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 0x7f63820c1430>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f63820c14c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f63820c1550>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f63820c15e0>", "_build": "<function ActorCriticPolicy._build at 0x7f63820c1670>", "forward": "<function ActorCriticPolicy.forward at 0x7f63820c1700>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f63820c1790>", "_predict": "<function ActorCriticPolicy._predict at 0x7f63820c1820>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f63820c18b0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f63820c1940>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f63820c19d0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f6382127ae0>"}, "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": 1657183629.2532454, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAGvHkb65n0k/3ME0v4TThL+DZ+w+Xb6EPgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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:ae966c0d34f8e0b91079f81ac2541b893a7b699a48b65c121278388f25a50228
+oid sha256:d818ba6e90a61090520f81dfff42251e2a242250e65b00de2d09210f1ebce839
 size 141436

ppo-LunarLander-v2/data

@@ -47,7 +47,7 @@
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1657183283.7582548,
+    "start_time": 1657183629.2532454,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "lr_schedule": {
@@ -56,7 +56,7 @@
     },
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAHCkqD7QFDc/HbJGPyVlgb8AZPS+dnlEvgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAGvHkb65n0k/3ME0v4TThL+DZ+w+Xb6EPgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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:bbcb9d37476605718fc8d38e468e41acb82d18c573a732c44bd315bf9a5ffac4
+oid sha256:3730401155f00e19da0c70b7174e6bc63746627e3957c2d28a87140de65bb877
 size 87545

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0f8d7f4e4dad659454a8e270e4dc79a43bd6d2cfa369a4cb2e27e668991e07a
+oid sha256:09e5688bd04b5bef1d52d61708549551786f16babe23b7e9a05a77e765e973df
 size 43073

results.json

@@ -1 +1 @@
-{"mean_reward": -194.728747, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 1, "eval_datetime": "2022-07-07T10:41:26.904175"}
+{"mean_reward": -247.756023, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 1, "eval_datetime": "2022-07-07T10:47:12.551688"}