Fixing first commit

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 0x0000015486347940>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x00000154863479D0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x0000015486347A60>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x0000015486347AF0>", "_build": "<function ActorCriticPolicy._build at 0x0000015486347B80>", "forward": "<function ActorCriticPolicy.forward at 0x0000015486347C10>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x0000015486347CA0>", "_predict": "<function ActorCriticPolicy._predict at 0x0000015486347D30>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x0000015486347DC0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x0000015486347E50>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x0000015486347EE0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x000001548634A480>"}, "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": 16, "num_timesteps": 507904, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1656425908.336002, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVhgIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAEsBSwFLE0MEiABTAJROhZQpjAFflIWUjFZDOlxVc2Vyc1x1dmQyMFwudmlydHVhbGVudnNcQ1YtZW52XGxpYlxzaXRlLXBhY2thZ2VzXHN0YWJsZV9iYXNlbGluZXMzXGNvbW1vblx1dGlscy5weZSMBGZ1bmOUS4BDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5RoDXVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "_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": -0.015808000000000044, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":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, "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": "Windows-10-10.0.22000-SP0 10.0.22000", "Python": "3.9.7", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu113", "GPU Enabled": "True", "Numpy": "1.22.3", "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 0x000002691A228940>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x000002691A2289D0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x000002691A228A60>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x000002691A228AF0>", "_build": "<function ActorCriticPolicy._build at 0x000002691A228B80>", "forward": "<function ActorCriticPolicy.forward at 0x000002691A228C10>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x000002691A228CA0>", "_predict": "<function ActorCriticPolicy._predict at 0x000002691A228D30>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x000002691A228DC0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x000002691A228E50>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x000002691A228EE0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x000002691A229C80>"}, "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": 16, "num_timesteps": 507904, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1656425908.336002, "learning_rate": 0.0003, "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": -0.015808000000000044, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVeRAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIwHebN06kWUCUhpRSlIwBbJRN6AOMAXSUR0B5gHKeTV2BdX2UKGgGaAloD0MISiandga8a0CUhpRSlGgVTaACaBZHQHmUl7Y02tN1fZQoaAZoCWgPQwjul09WjDlgQJSGlFKUaBVN6ANoFkdAeZeh9LHuJHV9lChoBmgJaA9DCJc48kBkSV5AlIaUUpRoFU3oA2gWR0B5mBi9Zid8dX2UKGgGaAloD0MI/WZiuhCLEECUhpRSlGgVTT8BaBZHQHmci4vvjOt1fZQoaAZoCWgPQwgSUOEIUuZiQJSGlFKUaBVN6ANoFkdAeacKhcqvvHV9lChoBmgJaA9DCJQw0/YvKWRAlIaUUpRoFU3oA2gWR0B5vunDR+jNdX2UKGgGaAloD0MIZoS3ByGqQkCUhpRSlGgVTegDaBZHQHnH/C/Glyl1fZQoaAZoCWgPQwgcz2dAPQFgQJSGlFKUaBVN6ANoFkdAec7x8UmD2HV9lChoBmgJaA9DCKSqCaJuSGNAlIaUUpRoFU3oA2gWR0B50RrqMWGidX2UKGgGaAloD0MI9z3qr1f1V0CUhpRSlGgVTegDaBZHQHnXZKODJ2d1fZQoaAZoCWgPQwg2r+qsFmZSQJSGlFKUaBVN6ANoFkdAedh3EyckMXV9lChoBmgJaA9DCOePaW0aOzxAlIaUUpRoFU3oA2gWR0B6Xt7w8W9EdX2UKGgGaAloD0MIJefEHtrRSUCUhpRSlGgVTegDaBZHQHpq40Q9RrJ1fZQoaAZoCWgPQwg3je21oDs0QJSGlFKUaBVN6ANoFkdAeoKh2nsLOXV9lChoBmgJaA9DCMaH2cu2bFVAlIaUUpRoFU3oA2gWR0B6jtlSS/0vdX2UKGgGaAloD0MIa7qe6LoZYkCUhpRSlGgVTegDaBZHQHq7vNZ/0/Z1fZQoaAZoCWgPQwimCkYldchMQJSGlFKUaBVN6ANoFkdAes5OMVDa5HV9lChoBmgJaA9DCOI6xhUXz11AlIaUUpRoFU3oA2gWR0B60S97F85TdX2UKGgGaAloD0MIndfYJSpzY0CUhpRSlGgVTegDaBZHQHrRpkK/mDF1fZQoaAZoCWgPQwhqT8k5scJlQJSGlFKUaBVN6ANoFkdAetYtb9qDb3V9lChoBmgJaA9DCCTusfShJ2FAlIaUUpRoFU3oA2gWR0B64OGlANXpdX2UKGgGaAloD0MIFYxK6gTOaUCUhpRSlGgVTVADaBZHQHrsj7yhBZ91fZQoaAZoCWgPQwhPQBNhw8sswJSGlFKUaBVLumgWR0B69RsBQvYfdX2UKGgGaAloD0MIJ0ut9xveW0CUhpRSlGgVTegDaBZHQHr39Ba9sad1fZQoaAZoCWgPQwggtB6+TI1aQJSGlFKUaBVN6ANoFkdAewBq3EyckXV9lChoBmgJaA9DCNvbLckBmWJAlIaUUpRoFU3oA2gWR0B7BzOSntOVdX2UKGgGaAloD0MIycovgzHgYUCUhpRSlGgVTSUDaBZHQHsI5cHGCI11fZQoaAZoCWgPQwhnnIaowhdRQJSGlFKUaBVN6ANoFkdAew8zk6tDD3V9lChoBmgJaA9DCODb9Gc/ZF9AlIaUUpRoFU3oA2gWR0B7EDWhAWzodX2UKGgGaAloD0MISl0yjpHyX0CUhpRSlGgVTegDaBZHQHuQjbi6xxF1fZQoaAZoCWgPQwgOoUrNHhRFQJSGlFKUaBVLzWgWR0B7npYHPeHjdX2UKGgGaAloD0MITE9Y4gEoW0CUhpRSlGgVTegDaBZHQHu3txMnJDF1fZQoaAZoCWgPQwgTYi6pWh5gQJSGlFKUaBVN6ANoFkdAe8Z7r9l2/3V9lChoBmgJaA9DCFw7URISkVpAlIaUUpRoFU3oA2gWR0B7+9hLGrCFdX2UKGgGaAloD0MI58WJr3bVXECUhpRSlGgVTegDaBZHQHwPQZn+Q2d1fZQoaAZoCWgPQwiwVYLF4VxbQJSGlFKUaBVN6ANoFkdAfBKNYr8R+XV9lChoBmgJaA9DCF9CBYcXgV5AlIaUUpRoFU3oA2gWR0B8Fz2AXl8xdX2UKGgGaAloD0MImGpmLQVQXkCUhpRSlGgVTegDaBZHQHwh/gR9PUN1fZQoaAZoCWgPQwiad5yio0xgQJSGlFKUaBVN6ANoFkdAfC4i48U21nV9lChoBmgJaA9DCNv66T9r0V5AlIaUUpRoFU3oA2gWR0B8NuuX/o7ndX2UKGgGaAloD0MIBHRfzmypXkCUhpRSlGgVTegDaBZHQHw5csMAmzB1fZQoaAZoCWgPQwiYio15HXH/v5SGlFKUaBVL12gWR0B8OcjFAE+xdX2UKGgGaAloD0MI/yQ+d4IcXkCUhpRSlGgVTegDaBZHQHxBCEDhcZ91fZQoaAZoCWgPQwjFVPoJZ1xfQJSGlFKUaBVN6ANoFkdAfEal8w5/9nV9lChoBmgJaA9DCBA//z346GJAlIaUUpRoFU3oA2gWR0B8TaIJqqOtdX2UKGgGaAloD0MI5XrbTAWKYUCUhpRSlGgVTegDaBZHQHxOh2r4nF51fZQoaAZoCWgPQwjNlNbfUpBxwJSGlFKUaBVLpWgWR0B8U42NvOyFdX2UKGgGaAloD0MIaVGf5A7LWUCUhpRSlGgVTegDaBZHQHxbJ0bLlmx1fZQoaAZoCWgPQwhPstXllDlcQJSGlFKUaBVN6ANoFkdAfOWo3rD633V9lChoBmgJaA9DCGZPAptzIFxAlIaUUpRoFU3oA2gWR0B8+snQY1pCdX2UKGgGaAloD0MILxnHSPZAVUCUhpRSlGgVTegDaBZHQH0IEZvUBn11fZQoaAZoCWgPQwgJGcizyzfjv5SGlFKUaBVL2GgWR0B9NRPhybQUdX2UKGgGaAloD0MI7j8yHTqYXECUhpRSlGgVTegDaBZHQH02a/Efkmx1fZQoaAZoCWgPQwgc7E0MydRkQJSGlFKUaBVN6ANoFkdAfUsBnzxwynV9lChoBmgJaA9DCN6QRgVOVmBAlIaUUpRoFU3oA2gWR0B9T6V2Rq46dX2UKGgGaAloD0MIogxVMZWqX0CUhpRSlGgVTegDaBZHQH1ahP0qYqp1fZQoaAZoCWgPQwjKpIY2ABlZQJSGlFKUaBVN6ANoFkdAfWbGh24d63V9lChoBmgJaA9DCHhgAOHD62RAlIaUUpRoFU3oA2gWR0B9b2ZE2HcldX2UKGgGaAloD0MIFclXAikZW0CUhpRSlGgVTegDaBZHQH1yDjJdSl51fZQoaAZoCWgPQwhj78UX7T9dQJSGlFKUaBVN6ANoFkdAfXrjLB9Cu3V9lChoBmgJaA9DCCXP9X04UF1AlIaUUpRoFU3oA2gWR0B9gcR02cawdX2UKGgGaAloD0MIQuvhy8S0Y0CUhpRSlGgVTegDaBZHQH2KLRSgoPV1fZQoaAZoCWgPQwgTmiSWlChfQJSGlFKUaBVN6ANoFkdAfYsrCFbml3V9lChoBmgJaA9DCHBh3Xj3sGFAlIaUUpRoFU3oA2gWR0B9kN1Tzd1udX2UKGgGaAloD0MI6lkQyvt+XkCUhpRSlGgVTegDaBZHQH2ZL0Bfa6B1fZQoaAZoCWgPQwjDLR9JSZVRQJSGlFKUaBVLo2gWR0B+IBVCHARDdX2UKGgGaAloD0MICVBTy9ZdYECUhpRSlGgVTegDaBZHQH4gIYm9g4R1fZQoaAZoCWgPQwgqH4Kq0acwQJSGlFKUaBVL4mgWR0B+Mb1AZ88cdX2UKGgGaAloD0MIAaQ2cfKPZ0CUhpRSlGgVTegDaBZHQH42BvvSc9Z1fZQoaAZoCWgPQwifd2NBYSw3QJSGlFKUaBVNHwFoFkdAfjYbdrO7hHV9lChoBmgJaA9DCD7shQK2JGBAlIaUUpRoFU3oA2gWR0B+c1rylN1ydX2UKGgGaAloD0MI7e9sj94kX0CUhpRSlGgVTegDaBZHQH50/LxI8Qt1fZQoaAZoCWgPQwjXFMjsLA5gQJSGlFKUaBVN6ANoFkdAfowHD7655XV9lChoBmgJaA9DCChFK/eC/2RAlIaUUpRoFU3oA2gWR0B+kPSeAd4ndX2UKGgGaAloD0MI54u9F19OXECUhpRSlGgVTegDaBZHQH6d5kkKNQ11fZQoaAZoCWgPQwjG+DB72chiQJSGlFKUaBVN6ANoFkdAfqst+TeO43V9lChoBmgJaA9DCD24O2u3FV9AlIaUUpRoFU3oA2gWR0B+tQUDdP+GdX2UKGgGaAloD0MIuXAgJAuMZECUhpRSlGgVTegDaBZHQH63pMHryDt1fZQoaAZoCWgPQwgxJCcTNwtiQJSGlFKUaBVN6ANoFkdAfsAr6ciGFnV9lChoBmgJaA9DCJDBilOtQllAlIaUUpRoFU3oA2gWR0B+xrMUypJgdX2UKGgGaAloD0MIP+WYLO71XUCUhpRSlGgVTegDaBZHQH7fHe7+T/11fZQoaAZoCWgPQwiastMP6ltiQJSGlFKUaBVN6ANoFkdAf2ueC04R3HV9lChoBmgJaA9DCGhYjLrWbVpAlIaUUpRoFU3oA2gWR0B/a65rgwXZdX2UKGgGaAloD0MI0/VE1wXwZECUhpRSlGgVTegDaBZHQH9+8D4gzP91fZQoaAZoCWgPQwiF6XsNQRtiQJSGlFKUaBVN6ANoFkdAf4Mplz2ex3V9lChoBmgJaA9DCK+XpghweldAlIaUUpRoFU3oA2gWR0B/gzn4fwI/dX2UKGgGaAloD0MIWkqWk1AGOUCUhpRSlGgVS/1oFkdAf52MHKOktXV9lChoBmgJaA9DCJq0qbpHDmJAlIaUUpRoFU3oA2gWR0B/vhejVQQ+dX2UKGgGaAloD0MIHSCYo8csZECUhpRSlGgVTegDaBZHQH+/jF+/gzh1fZQoaAZoCWgPQwhYx/FDpYBiQJSGlFKUaBVN6ANoFkdAf9TYJmdy1nV9lChoBmgJaA9DCCHNWDSdpWRAlIaUUpRoFU3oA2gWR0B/2eZ6Uqx1dX2UKGgGaAloD0MIxFxStd3gOECUhpRSlGgVTegDaBZHQH/l7qt5le51fZQoaAZoCWgPQwgB2lazTs9kQJSGlFKUaBVN6ANoFkdAf/OELpiZv3V9lChoBmgJaA9DCAJKQ41Cq2BAlIaUUpRoFU3oA2gWR0B//A9yLhrFdX2UKGgGaAloD0MIqWkX00y9X0CUhpRSlGgVTegDaBZHQH/+ccIZ62R1fZQoaAZoCWgPQwj2e2KdKgFYQJSGlFKUaBVN6ANoFkdAgAMFuejEenV9lChoBmgJaA9DCOOqsu8KzmBAlIaUUpRoFU3oA2gWR0CABeLpiZv2dX2UKGgGaAloD0MIuvYF9MKlVECUhpRSlGgVTegDaBZHQIAQ9nTRYzV1fZQoaAZoCWgPQwg826M33AVlQJSGlFKUaBVN6ANoFkdAgBiGtQsPKHVlLg=="}, "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": "Windows-10-10.0.22000-SP0 10.0.22000", "Python": "3.9.7", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu113", "GPU Enabled": "True", "Numpy": "1.22.3", "Gym": "0.21.0"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d684dae11b6ae04d03e5d2678193bcaae2682f712aa94efd05ada684d94597b7
+oid sha256:526315c1c2ef055cdb7b5efaf18100734c44605b798a6dae76ece940ac201db4
 size 142962

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 0x0000015486347940>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x00000154863479D0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x0000015486347A60>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x0000015486347AF0>",
-        "_build": "<function ActorCriticPolicy._build at 0x0000015486347B80>",
-        "forward": "<function ActorCriticPolicy.forward at 0x0000015486347C10>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x0000015486347CA0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x0000015486347D30>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x0000015486347DC0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x0000015486347E50>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x0000015486347EE0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x000002691A228940>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x000002691A2289D0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x000002691A228A60>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x000002691A228AF0>",
+        "_build": "<function ActorCriticPolicy._build at 0x000002691A228B80>",
+        "forward": "<function ActorCriticPolicy.forward at 0x000002691A228C10>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x000002691A228CA0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x000002691A228D30>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x000002691A228DC0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x000002691A228E50>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x000002691A228EE0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x000001548634A480>"
+        "_abc_impl": "<_abc._abc_data object at 0x000002691A229C80>"
     },
     "verbose": 1,
     "policy_kwargs": {},

results.json

@@ -1 +1 @@
-{"mean_reward": 218.31438213810694, "std_reward": 23.141367550845832, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-28T17:30:15.303735"}
+{"mean_reward": 222.8651214590017, "std_reward": 47.035842961432465, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-28T17:39:21.002187"}