Upload PPO FrozenLake-v1 trained agent

FrozenLake-v1-version_0_0_2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9257c5f4db12f4abd78afb4e8d8188c61d8b50c1e9cea9f918742a314256f3c9
-size 156700
+oid sha256:fd7b51f031a1bb31e51a5018f2e94565c2d0fc1114dcac17b6dde1e10c060d40
+size 230428

FrozenLake-v1-version_0_0_2/data

@@ -22,8 +22,8 @@
     "policy_kwargs": {},
     "observation_space": {
         ":type:": "<class 'gym.spaces.discrete.Discrete'>",
-        ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLEIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
-        "n": 16,
+        ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLQIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        "n": 64,
         "_shape": [],
         "dtype": "int64",
         "_np_random": null
@@ -42,7 +42,7 @@
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1670430115745126688,
+    "start_time": 1670431053568105410,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "lr_schedule": {
@@ -51,11 +51,11 @@
     },
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWV8wAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAEAAAAAAAAAAgAAAAAAAAACQAAAAAAAAAEAAAAAAAAAA4AAAAAAAAADQAAAAAAAAAJAAAAAAAAAAQAAAAAAAAACAAAAAAAAAAEAAAAAAAAAAQAAAAAAAAADgAAAAAAAAAKAAAAAAAAAAQAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="
+        ":serialized:": "gAWV8wAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAACcAAAAAAAAANwAAAAAAAAABAAAAAAAAABUAAAAAAAAAAQAAAAAAAAAOAAAAAAAAAAAAAAAAAAAADQAAAAAAAAADAAAAAAAAACcAAAAAAAAAAwAAAAAAAAACAAAAAAAAAC8AAAAAAAAANwAAAAAAAAAAAAAAAAAAAA4AAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAEBAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAEAAAAAAAAAAQCUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
     },
     "_last_original_obs": null,
     "_episode_num": 0,
@@ -64,7 +64,7 @@
     "_current_progress_remaining": -0.0027007999999999477,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",

FrozenLake-v1-version_0_0_2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f406a5f12e59126fa329b7f50eccc3bb6662c4bdada3620fc8d3bd59c6b431eb
-size 96057
+oid sha256:9f7df3115d073732124a4dad567e64caa5978e5a2c0993004e9fc202ac27aca6
+size 145209

FrozenLake-v1-version_0_0_2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dae72de36c568837d8f889babb3f6a19b1438db74b3bdcc2d4ef691626a2363d
-size 47297
+oid sha256:19b03b6d70bd8cda2042cc1bd5b9f99a0b8981132727cbf8a841f5dd0065b5d8
+size 71873

README.md

@@ -16,7 +16,7 @@ model-index:
       type: FrozenLake-v1
     metrics:
     - type: mean_reward
-      value: 0.10 +/- 0.30
+      value: 0.20 +/- 0.40
       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 0x7f2d632a41f0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f2d632a4280>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f2d632a4310>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f2d632a43a0>", "_build": "<function ActorCriticPolicy._build at 0x7f2d632a4430>", "forward": "<function ActorCriticPolicy.forward at 0x7f2d632a44c0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f2d632a4550>", "_predict": "<function ActorCriticPolicy._predict at 0x7f2d632a45e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f2d632a4670>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f2d632a4700>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f2d632a4790>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f2d6329d7b0>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLEIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 16, "_shape": [], "dtype": "int64", "_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": 16, "num_timesteps": 2506752, "_total_timesteps": 2500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1670430115745126688, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWV8wAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAEAAAAAAAAAAgAAAAAAAAACQAAAAAAAAAEAAAAAAAAAA4AAAAAAAAADQAAAAAAAAAJAAAAAAAAAAQAAAAAAAAACAAAAAAAAAAEAAAAAAAAAAQAAAAAAAAADgAAAAAAAAAKAAAAAAAAAAQAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAEBAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.0027007999999999477, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 612, "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-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.8.15", "Stable-Baselines3": "1.6.2", "PyTorch": "1.12.1+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "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 0x7f2d632a41f0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f2d632a4280>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f2d632a4310>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f2d632a43a0>", "_build": "<function ActorCriticPolicy._build at 0x7f2d632a4430>", "forward": "<function ActorCriticPolicy.forward at 0x7f2d632a44c0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f2d632a4550>", "_predict": "<function ActorCriticPolicy._predict at 0x7f2d632a45e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f2d632a4670>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f2d632a4700>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f2d632a4790>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f2d6329d7b0>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLQIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 64, "_shape": [], "dtype": "int64", "_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": 16, "num_timesteps": 2506752, "_total_timesteps": 2500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1670431053568105410, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWV8wAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAACcAAAAAAAAANwAAAAAAAAABAAAAAAAAABUAAAAAAAAAAQAAAAAAAAAOAAAAAAAAAAAAAAAAAAAADQAAAAAAAAADAAAAAAAAACcAAAAAAAAAAwAAAAAAAAACAAAAAAAAAC8AAAAAAAAANwAAAAAAAAAAAAAAAAAAAA4AAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAEAAAAAAAAAAQCUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.0027007999999999477, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 612, "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-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.8.15", "Stable-Baselines3": "1.6.2", "PyTorch": "1.12.1+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}

results.json

@@ -1 +1 @@
-{"mean_reward": 0.1, "std_reward": 0.30000000000000004, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-07T16:37:24.491556"}
+{"mean_reward": 0.2, "std_reward": 0.4000000000000001, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-07T16:53:00.668133"}