new! 3

README.md

@@ -16,7 +16,7 @@ model-index:
       type: FrozenLake-v1
     metrics:
     - type: mean_reward
-      value: 1.00 +/- 0.00
+      value: 0.00 +/- 0.00
       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 0x7fe7d6b28160>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fe7d6b281f0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fe7d6b28280>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fe7d6b28310>", "_build": "<function ActorCriticPolicy._build at 0x7fe7d6b283a0>", "forward": "<function ActorCriticPolicy.forward at 0x7fe7d6b28430>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fe7d6b284c0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fe7d6b28550>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fe7d6b285e0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fe7d6b28670>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fe7d6b28700>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fe7d6b1ea50>"}, "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": 507904, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1670280979194778505, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWV8wAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAAQAAAAAAAAAAAAAAAAAAAAEAAAAAAAAAAUAAAAAAAAADgAAAAAAAAAFAAAAAAAAAAAAAAAAAAAACgAAAAAAAAAJAAAAAAAAAAEAAAAAAAAAAAAAAAAAAAAEAAAAAAAAAAQAAAAAAAAACgAAAAAAAAAAAAAAAAAAAAEAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAABAAAAAAEAAAABAAAAAQCUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWV4AsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHP/AAAAAAAACMAWyUSwaMAXSUR0BonHtdAxBWdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonZdnkDISdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonQnBtUGWdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonKy6cy31dX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonI/qxC6ZdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonNdPci4bdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonKwSrYGudX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonNtGd7OWdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonbUAksz3dX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonTvXsgMddX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BondRceKbbdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0Boncdkrf+CdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonbjYI0IkdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonOpOvdM1dX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonNvybx3FdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonNRUFSsKdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonMAaNuLrdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0Bondk1/DtPdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonUuJ1q33dX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonO6XjU/fdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonNG7SRbKdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonRguyu6mdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonOz4UN8WdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonRvgm7aqdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonfVurIYFdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonXxpcophdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonhPl+3H8dX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BongbfgrH3dX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonfhS9/SZdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonSnHeaa1dX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonRtrKvFFdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonRPO6d1/dX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonP9zfaYedX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonhqM3qA0dX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonYzi0fHQdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonS/bj94vdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonRMSK3uvdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonVmDlHSXdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonS5NGmUGdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonV07r9l3dX2UKGgGRz/wAAAAAAAAaAdLBmgIR0Bonjc6/7BPdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0Bonb4SHuZ1dX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonlWZJCjUdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonkiUxEfDdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonjoGIKtxdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonWt4iX6ZdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonV0cOskqdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonVV/+bVjdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonUEidJ8OdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonlpItlI3dX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonczCUHIIdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonW+9Jz1cdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonVLeyiVTdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonZlSS/0vdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonW4XoC+2dX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonZzijtXxdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonnaFmFrVdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0Bonf1ct5D7dX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonpTfixVydX2UKGgGRz/wAAAAAAAAaAdLBmgIR0Bonof8uSOjdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonarJbMX8dX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonZxtHhCMdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonZTQ3PzGdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonYB1cMVldX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonplxwQ18dX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BongvDgqEwdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0Bona68QI2PdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonZHmRvFWdX2UKGgGRz/wAAAAAAAAaAdLCGgIR0Bono7eVLSNdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BondqtYB/7dX2UKGgGRz/wAAAAAAAAaAdLBmgIR0Bona9sabWmdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0Bond83Mpw0dX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonrksBhhIdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonkABDG96dX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BontejVQQ+dX2UKGgGRz/wAAAAAAAAaAdLBmgIR0Bonsqc3EQ5dX2UKGgGRz/wAAAAAAAAaAdLBmgIR0Bone1pj+aSdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0Bond8NQTEjdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonddxAB1cdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BoncMVk+X7dX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BontwFTvRadX2UKGgGRz/wAAAAAAAAaAdLBmgIR0Bonk5fdAPedX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonfFWGRFJdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BondR1oxpMdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BontLL6k6+dX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonhysCDEndX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonfFtKqXGdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BoniBy0a60dX2UKGgGRz/wAAAAAAAAaAdLBmgIR0Bonvt8eCCjdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonoJRfnfVdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonxokAxSHdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0Bonw0fozN2dX2UKGgGRz/wAAAAAAAAaAdLBmgIR0Boni/ub7TEdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BoniGSIP9UdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0Bonhn13+uOdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BongWac7QtdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0Bonx/d69kCdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonpI4EOiGdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonjUy57PZdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0BonhhScbzcdWUu"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 124, "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 0x7f5f054f41f0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f5f054f4280>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f5f054f4310>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f5f054f43a0>", "_build": "<function ActorCriticPolicy._build at 0x7f5f054f4430>", "forward": "<function ActorCriticPolicy.forward at 0x7f5f054f44c0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f5f054f4550>", "_predict": "<function ActorCriticPolicy._predict at 0x7f5f054f45e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f5f054f4670>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f5f054f4700>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f5f054f4790>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f5f0556af60>"}, "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": 524288, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1672598345259342226, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWV8wAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAAsAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAoAAAAAAAAABgAAAAAAAAAFAAAAAAAAAAQAAAAAAAAACQAAAAAAAAAAAAAAAAAAAAQAAAAAAAAABQAAAAAAAAAFAAAAAAAAAAsAAAAAAAAACwAAAAAAAAAKAAAAAAAAAAoAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAABAQAAAAAAAQAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.04857599999999995, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWV4AsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHP/AAAAAAAACMAWyUSwaMAXSUR0B6SErvsqrjdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SHdcjZ+QdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SGKQ7tAtdX2UKGgGRz/wAAAAAAAAaAdLCmgIR0B6SF1MdtEYdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SFPpIMBqdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SFxyXD3udX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SIQoTfzjdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SH0h/y5JdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SF2ovSMMdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SFWT5ftydX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SFKtga3rdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SG+UQkHEdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SGCROk+HdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SF2+wkgPdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SIVfu1F6dX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SHo2XLNfdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SJc/t6X0dX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SIJUo8ZDdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SH0OEug6dX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SHO2RaHLdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SHyAhB7edX2UKGgGRz/wAAAAAAAAaAdLCGgIR0B6SHaBZpztdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SKWJJoTPdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SH8AJb+tdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SHbeuV5bdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SHP2PDHfdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SJDMNc4YdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SIHJLdvbdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SH72tdRjdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SKaPS2H+dX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SJtl7MPjdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SLh60IC2dX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SKOU+s5odX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SJ5Pdl/ZdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SJdrwe/6dX2UKGgGRz/wAAAAAAAAaAdLCGgIR0B6SJ9x6v7ndX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SMYFaB7NdX2UKGgGRz/wAAAAAAAAaAdLDGgIR0B6SL8EV32VdX2UKGgGRz/wAAAAAAAAaAdLCGgIR0B6SKi7CiyqdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SJeNT987dX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SJSl3yI6dX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SKJaaCtjdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SJ+MIeHSdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SMc6vJRwdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SLwTdtVJdX2UKGgGRz/wAAAAAAAAaAdLCGgIR0B6SKp6yB07dX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SMRe1KGtdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SL8cdYGMdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SLgVGkN4dX2UKGgGRz/wAAAAAAAAaAdLCGgIR0B6SOPU8V59dX2UKGgGRz/wAAAAAAAAaAdLCmgIR0B6SMa5wwTNdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SMA3kxREdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SOYx+KCQdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SMiliz9kdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SLSOR1YAdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SMKZ2IO6dX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SL/Q0GeMdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SOfI0ZWJdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SMrz5GjLdX2UKGgGRz/wAAAAAAAAaAdLCGgIR0B6SMLSeAd5dX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SOTGHYYjdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SN+NLlFMdX2UKGgGRz/wAAAAAAAAaAdLCmgIR0B6SPUUfxMGdX2UKGgGRz/wAAAAAAAAaAdLCGgIR0B6SOdBjWkKdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SNiXpnpTdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SOgRK6FudX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SOGWUr08dX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SQis4ku6dX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SOslsxfwdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SNcu8K5TdX2UKGgGRz/wAAAAAAAAaAdLCGgIR0B6SRFH8TBZdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SOUgSvkjdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SOJP69CedX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SQpSaVlgdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SOV2Rq46dX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SQf3evZAdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SQK4QSSNdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SRiz9jwydX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SQrupjtpdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SPxI8QqadX2UKGgGRz/wAAAAAAAAaAdLCGgIR0B6SPlijL0SdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SQtdzGPxdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SQTewcHXdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SSr6tT1kdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SQ11nuiOdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SPlaKUFCdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6STOC5EtvdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SQdgfEGadX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SQSPEKmbdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SSw5eZ5SdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SQdV/+bWdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SSl+EytWdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SSyE+PildX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SR3dKujidX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SRr1uivgdX2UKGgGRz/wAAAAAAAAaAdLCGgIR0B6SS9i+cpcdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SSYG+sYEdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SUv/R3NcdX2UKGgGRz/wAAAAAAAAaAdLCGgIR0B6SUT4+KTCdX2UKGgGRz/wAAAAAAAAaAdLBmgIR0B6SS6BiCrcdWUu"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 160, "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, "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": "3.8.16", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu116", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}

ppo-FrozenLake-v1.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e02f927a6de9eb2e9d70d0ff33675f3b863f38b9477480d3d8366781d7014d1
-size 156697
+oid sha256:323977c615dd92690dca9c3ecf0f2caa177eca83da0a84028d66a832f49503d1
+size 156759

ppo-FrozenLake-v1/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 0x7fe7d6b28160>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fe7d6b281f0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fe7d6b28280>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fe7d6b28310>",
-        "_build": "<function ActorCriticPolicy._build at 0x7fe7d6b283a0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7fe7d6b28430>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fe7d6b284c0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7fe7d6b28550>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fe7d6b285e0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fe7d6b28670>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fe7d6b28700>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f5f054f41f0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f5f054f4280>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f5f054f4310>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f5f054f43a0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f5f054f4430>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f5f054f44c0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f5f054f4550>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f5f054f45e0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f5f054f4670>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f5f054f4700>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f5f054f4790>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x7fe7d6b1ea50>"
+        "_abc_impl": "<_abc_data object at 0x7f5f0556af60>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -37,12 +37,12 @@
         "_np_random": null
     },
     "n_envs": 16,
-    "num_timesteps": 507904,
+    "num_timesteps": 524288,
     "_total_timesteps": 500000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1670280979194778505,
+    "start_time": 1672598345259342226,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "lr_schedule": {
@@ -51,34 +51,34 @@
     },
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWV8wAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAAQAAAAAAAAAAAAAAAAAAAAEAAAAAAAAAAUAAAAAAAAADgAAAAAAAAAFAAAAAAAAAAAAAAAAAAAACgAAAAAAAAAJAAAAAAAAAAEAAAAAAAAAAAAAAAAAAAAEAAAAAAAAAAQAAAAAAAAACgAAAAAAAAAAAAAAAAAAAAEAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="
+        ":serialized:": "gAWV8wAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAAsAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAoAAAAAAAAABgAAAAAAAAAFAAAAAAAAAAQAAAAAAAAACQAAAAAAAAAAAAAAAAAAAAQAAAAAAAAABQAAAAAAAAAFAAAAAAAAAAsAAAAAAAAACwAAAAAAAAAKAAAAAAAAAAoAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAABAAAAAAEAAAABAAAAAQCUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAABAQAAAAAAAQAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
     },
     "_last_original_obs": null,
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.015808000000000044,
+    "_current_progress_remaining": -0.04857599999999995,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 124,
-    "n_steps": 1024,
-    "gamma": 0.999,
-    "gae_lambda": 0.98,
-    "ent_coef": 0.01,
+    "_n_updates": 160,
+    "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": 4,
+    "n_epochs": 10,
     "clip_range": {
         ":type:": "<class 'function'>",
         ":serialized:": "gAWVwwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4BDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/yZmZmZmZmoWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="

ppo-FrozenLake-v1/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fbccc0540d80ec5793484463ed9aa3aa1fc34e6d6b654677533b34db5c360e6
-size 96057
+oid sha256:44884372d099d2fc08ff647174c55aa04124066399b389563a1051dc9e0f3c6a
+size 96121

ppo-FrozenLake-v1/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37c15a13eeeb3d7a465fb7a6d13a44e767f421d1cd3a1aa5e1a675ce151c40b0
+oid sha256:dae0833e6dd79efc2a57caa602314199c055257b7371ce62beb498d3aef409ad
 size 47297

ppo-FrozenLake-v1/system_info.txt

@@ -1,7 +1,7 @@
 OS: Linux-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022
-Python: 3.8.15
+Python: 3.8.16
 Stable-Baselines3: 1.6.2
-PyTorch: 1.12.1+cu113
+PyTorch: 1.13.0+cu116
 GPU Enabled: True
 Numpy: 1.21.6
 Gym: 0.21.0

results.json

@@ -1 +1 @@
-{"mean_reward": 1.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-05T23:00:57.358916"}
+{"mean_reward": 0.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-01T19:41:38.949259"}