Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -527.45 +/- 131.56
+      value: -89.00 +/- 41.18
       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 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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 0x7fed936be3a0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fed936be430>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fed936be4c0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fed936be550>", "_build": "<function ActorCriticPolicy._build at 0x7fed936be5e0>", "forward": "<function ActorCriticPolicy.forward at 0x7fed936be670>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fed936be700>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fed936be790>", "_predict": "<function ActorCriticPolicy._predict at 0x7fed936be820>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fed936be8b0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fed936be940>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fed936be9d0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fed936b4b10>"}, "verbose": 0, "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": 1, "num_timesteps": 100455, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1676863652895088662, "learning_rate": 0.4901809325786132, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAKZgn71U+Z4/DmX0vrQOJb+YjAQ/M7lmPwAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -0.004550000000000054, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVHRAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIUS6NX1gEgsCUhpRSlIwBbJRLP4wBdJRHQG1EdupCKJl1fZQoaAZoCWgPQwgzNJ4IIvSAwJSGlFKUaBVLRWgWR0BtRy3d9Dx9dX2UKGgGaAloD0MIweRGkfVmesCUhpRSlGgVSztoFkdAbUmGjbi6x3V9lChoBmgJaA9DCJIDdjW5F3jAlIaUUpRoFUszaBZHQG1Lnkkrwvx1fZQoaAZoCWgPQwg1QdR9wHZ/wJSGlFKUaBVLOWgWR0BtTeqrBCUpdX2UKGgGaAloD0MICYofY+5fe8CUhpRSlGgVS0toFkdAbVD5tWMjvHV9lChoBmgJaA9DCF/U7lchlYXAlIaUUpRoFUtMaBZHQG1tjy4FzMl1fZQoaAZoCWgPQwjUm1HzlbN7wJSGlFKUaBVLNGgWR0Btb5aV2Rq5dX2UKGgGaAloD0MIDJQUWMAiisCUhpRSlGgVS09oFkdAbXK1KGtZFHV9lChoBmgJaA9DCDeMguBRDozAlIaUUpRoFUtTaBZHQG12Bg/keZJ1fZQoaAZoCWgPQwiH/gkuthaHwJSGlFKUaBVLT2gWR0BteSHKwIMSdX2UKGgGaAloD0MIlZwTe4iNgsCUhpRSlGgVS0RoFkdAbXvckdFOPHV9lChoBmgJaA9DCJiiXBo/UnbAlIaUUpRoFUszaBZHQG191gx8D0V1fZQoaAZoCWgPQwhmMEYkygKDwJSGlFKUaBVLQ2gWR0BtgJj2Bas7dX2UKGgGaAloD0MIuAchIB9Pf8CUhpRSlGgVS0doFkdAbYOvugHu7nV9lChoBmgJaA9DCEfku5Saq4fAlIaUUpRoFUtPaBZHQG2HDbBXS0B1fZQoaAZoCWgPQwjhCijUs5GGwJSGlFKUaBVLSmgWR0Btie/rSmZWdX2UKGgGaAloD0MIMzUJ3tAIgsCUhpRSlGgVSz9oFkdAbYx3UQTVUnV9lChoBmgJaA9DCGMnvASnGYjAlIaUUpRoFUtTaBZHQG2P0ipvP1N1fZQoaAZoCWgPQwiCV8udOWiGwJSGlFKUaBVLTWgWR0BtrE+xGDtgdX2UKGgGaAloD0MIjjwQWeTrecCUhpRSlGgVSztoFkdAba6/jbSJCXV9lChoBmgJaA9DCCCXOPJAW3vAlIaUUpRoFUs2aBZHQG2w9eY2Kl51fZQoaAZoCWgPQwj0N6EQAVp5wJSGlFKUaBVLN2gWR0Bts1NWU8msdX2UKGgGaAloD0MIfxR15h6Kd8CUhpRSlGgVSzRoFkdAbbVlpXZGrnV9lChoBmgJaA9DCIm1+BSAooTAlIaUUpRoFUtJaBZHQG24UCRwIdF1fZQoaAZoCWgPQwjdskP8w+Z9wJSGlFKUaBVLN2gWR0BtunskY4yXdX2UKGgGaAloD0MI8Ps3L84Hj8CUhpRSlGgVS1ZoFkdAbb4gjhUBGXV9lChoBmgJaA9DCAirsYS16HTAlIaUUpRoFUszaBZHQG3AQeNkvsZ1fZQoaAZoCWgPQwgf963WiTN7wJSGlFKUaBVLPGgWR0BtwrUqhDgJdX2UKGgGaAloD0MIGeYEbRKrhsCUhpRSlGgVS0poFkdAbcX80k4WDnV9lChoBmgJaA9DCNSAQdJn34DAlIaUUpRoFUs5aBZHQG3IQm/nGKh1fZQoaAZoCWgPQwhUHAdebeBzwJSGlFKUaBVLMmgWR0BtykKVpsXSdX2UKGgGaAloD0MIWB8PfTdWesCUhpRSlGgVSzFoFkdAbcxnPE87p3V9lChoBmgJaA9DCGXEBaCx7YbAlIaUUpRoFUtMaBZHQG3PkcbR4Ql1fZQoaAZoCWgPQwjjwRa7fQiOwJSGlFKUaBVLVGgWR0Bt7Jsj3VTadX2UKGgGaAloD0MIZmoSvMEhhMCUhpRSlGgVS0toFkdAbe+69TP0I3V9lChoBmgJaA9DCL5muWy0JHPAlIaUUpRoFUsyaBZHQG3xwZGax5d1fZQoaAZoCWgPQwgFwk6xKtR1wJSGlFKUaBVLNGgWR0Bt8+lyimEXdX2UKGgGaAloD0MI10//WZPHjMCUhpRSlGgVS1VoFkdAbfdnJT2nKnV9lChoBmgJaA9DCM14W+lVoIPAlIaUUpRoFUs/aBZHQG354cWCVbB1fZQoaAZoCWgPQwjDSgUVVXGBwJSGlFKUaBVLO2gWR0Bt/EA5q/M4dX2UKGgGaAloD0MISgwCK0d0iMCUhpRSlGgVS09oFkdAbf+G5+Ytx3V9lChoBmgJaA9DCGA6rdvAqYXAlIaUUpRoFUtJaBZHQG4Cr8aXKKZ1fZQoaAZoCWgPQwiiKqbSrwqCwJSGlFKUaBVLPmgWR0BuBTKifxtpdX2UKGgGaAloD0MIYYicvl5BfMCUhpRSlGgVS0poFkdAbghn9vS+g3V9lChoBmgJaA9DCCxGXWtvLITAlIaUUpRoFUteaBZHQG4MSVObiId1fZQoaAZoCWgPQwie6/twEG17wJSGlFKUaBVLPGgWR0BuDtHxz7uVdX2UKGgGaAloD0MIjSeCOE+qf8CUhpRSlGgVSzpoFkdAbiryAhB7eHV9lChoBmgJaA9DCAgCZOj4gILAlIaUUpRoFUs/aBZHQG4tiT+vQnh1fZQoaAZoCWgPQwg095DwfTOEwJSGlFKUaBVLQWgWR0BuMEpTdcjadX2UKGgGaAloD0MIg2itaLPzdcCUhpRSlGgVSzJoFkdAbjJiKiwjdHV9lChoBmgJaA9DCBcplIXvdnrAlIaUUpRoFUs1aBZHQG40jK5kK/p1fZQoaAZoCWgPQwgi/mFLz7J5wJSGlFKUaBVLOGgWR0BuNsKXv6TGdX2UKGgGaAloD0MIodefxMfrh8CUhpRSlGgVS1RoFkdAbjo5bQkX13V9lChoBmgJaA9DCJKRs7Ano3/AlIaUUpRoFUtHaBZHQG49ZlOGj9J1fZQoaAZoCWgPQwiBsilX2FSLwJSGlFKUaBVLUmgWR0BuQMSTQmeEdX2UKGgGaAloD0MIofKv5ZWsdcCUhpRSlGgVSzJoFkdAbkK/OdGy5nV9lChoBmgJaA9DCOV/8ncvZ3zAlIaUUpRoFUs2aBZHQG5E8WsRxtJ1fZQoaAZoCWgPQwjY1k//uTqHwJSGlFKUaBVLUWgWR0BuSJqEeyRkdX2UKGgGaAloD0MImdh8XHssh8CUhpRSlGgVS1FoFkdAbkv/ZuhsZnV9lChoBmgJaA9DCOAUVipI4YLAlIaUUpRoFUtBaBZHQG5pir1dxAB1fZQoaAZoCWgPQwhne/SGO5N8wJSGlFKUaBVLPmgWR0BubBOvdM0xdX2UKGgGaAloD0MIpGyRtLsMh8CUhpRSlGgVS1FoFkdAbm9lf7aZhXV9lChoBmgJaA9DCGU3M/oRHoHAlIaUUpRoFUtEaBZHQG5yKoIfKZF1fZQoaAZoCWgPQwj8yK1J96x2wJSGlFKUaBVLMmgWR0BudGAbyYoidX2UKGgGaAloD0MICAPPvYcggcCUhpRSlGgVSztoFkdAbnbW3BpHqnV9lChoBmgJaA9DCAwBwLHnroDAlIaUUpRoFUs6aBZHQG56WcawUxp1fZQoaAZoCWgPQwiTxf1H5sKFwJSGlFKUaBVLRmgWR0BufoIIF/x2dX2UKGgGaAloD0MI443MI391eMCUhpRSlGgVSzNoFkdAboFlOoHcDnV9lChoBmgJaA9DCBYYsrrVV3fAlIaUUpRoFUsyaBZHQG6EBTn7pFF1fZQoaAZoCWgPQwjw37w4MaZ7wJSGlFKUaBVLNGgWR0Buhr5IpYs/dX2UKGgGaAloD0MI0qdV9IdthMCUhpRSlGgVS0ZoFkdAbosW1MM7VHV9lChoBmgJaA9DCCi4WFHj5oPAlIaUUpRoFUtDaBZHQG6O+Sr5qM51fZQoaAZoCWgPQwhZ/Kawknt8wJSGlFKUaBVLSmgWR0BukuHzpX6qdX2UKGgGaAloD0MInaG4442LgMCUhpRSlGgVS0FoFkdAbpZJwKjSHHV9lChoBmgJaA9DCAdA3NXr8IrAlIaUUpRoFUtYaBZHQG696qjrRjV1fZQoaAZoCWgPQwgOTkS/NtyDwJSGlFKUaBVLRWgWR0BuwflGPPszdX2UKGgGaAloD0MIBYiCGROiicCUhpRSlGgVS1RoFkdAbsaA7PppvnV9lChoBmgJaA9DCFyPwvWIeobAlIaUUpRoFUtJaBZHQG7KYnndO7B1fZQoaAZoCWgPQwjz4y8tyvaFwJSGlFKUaBVLU2gWR0Buz163RXwLdX2UKGgGaAloD0MILbKd74c4hMCUhpRSlGgVS0NoFkdAbtLz4DcM3XV9lChoBmgJaA9DCKeVQiCXIYPAlIaUUpRoFUtVaBZHQG7X3fZVXFN1fZQoaAZoCWgPQwg4L058dcx+wJSGlFKUaBVLN2gWR0Bu2wMtsenydX2UKGgGaAloD0MInkXvVMCKgMCUhpRSlGgVSz1oFkdAbt6Xv6TGHnV9lChoBmgJaA9DCG9iSE4GXYHAlIaUUpRoFUs+aBZHQG7iKWLP2PF1fZQoaAZoCWgPQwjqJcYynU+FwJSGlFKUaBVLTmgWR0Bu5vz6JqIrdX2UKGgGaAloD0MIvAfovhz4ecCUhpRSlGgVSzhoFkdAbuqJIDoyK3V9lChoBmgJaA9DCCm0rPsHYYjAlIaUUpRoFUtPaBZHQG8YhoduHet1fZQoaAZoCWgPQwgP1ZRk3Ud+wJSGlFKUaBVLPGgWR0BvHEYXO4XodX2UKGgGaAloD0MIWtk+5O2FfcCUhpRSlGgVSzVoFkdAbx+EM9bHInV9lChoBmgJaA9DCAJKQ40ieIjAlIaUUpRoFUtUaBZHQG8lCbtqpLp1fZQoaAZoCWgPQwie0OtPAp2GwJSGlFKUaBVLSGgWR0BvKUrNGEwndX2UKGgGaAloD0MIeZCeIufZhcCUhpRSlGgVS09oFkdAby4gIQe3hHV9lChoBmgJaA9DCP4N2qsPgH3AlIaUUpRoFUs3aBZHQG8xenQ6ZIB1fZQoaAZoCWgPQwhJaMu51Il2wJSGlFKUaBVLbmgWR0BvOHMnqmj1dX2UKGgGaAloD0MIGk6Zmy9GicCUhpRSlGgVS01oFkdAbz1GiHqNZXV9lChoBmgJaA9DCHRfzmyXf37AlIaUUpRoFUtIaBZHQG9BSsKb8WN1fZQoaAZoCWgPQwjTodPzjsCBwJSGlFKUaBVLRGgWR0BvRBoTPBzndX2UKGgGaAloD0MIMNgN21Zch8CUhpRSlGgVS05oFkdAb0dAtWdVenV9lChoBmgJaA9DCCNm9nnMfILAlIaUUpRoFUtBaBZHQG9JxRl6JIl1ZS4="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 1110, "n_steps": 905, "gamma": 0.000866430802601825, "gae_lambda": 0.015423116225634408, "ent_coef": 0.027609273631136383, "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-5.10.147+-x86_64-with-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.8.10", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu116", "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 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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 0x7eff0fe724c0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7eff0fe72550>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7eff0fe725e0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7eff0fe72670>", "_build": "<function ActorCriticPolicy._build at 0x7eff0fe72700>", "forward": "<function ActorCriticPolicy.forward at 0x7eff0fe72790>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7eff0fe72820>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7eff0fe728b0>", "_predict": "<function ActorCriticPolicy._predict at 0x7eff0fe72940>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7eff0fe729d0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7eff0fe72a60>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7eff0fe72af0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7eff0fe6aa50>"}, "verbose": 0, "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": 1, "num_timesteps": 0, "_total_timesteps": 0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": null, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": null, "_last_episode_starts": null, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 1, "ep_info_buffer": null, "ep_success_buffer": null, "_n_updates": 0, "n_steps": 1024, "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-5.10.147+-x86_64-with-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.8.10", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu116", "GPU Enabled": "False", "Numpy": "1.21.6", "Gym": "0.21.0"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6da60886c37085ca5927f98e5902a0aed3c3f354ce55609583baecb4827664f5
-size 146689
+oid sha256:e3958bc2503999e418fde027561a0952e21e208f49faf36a043b6ccac560135d
+size 52940

ppo-LunarLander-v2/data

@@ -4,20 +4,20 @@
         ":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 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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 0x7fed936be3a0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fed936be430>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fed936be4c0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fed936be550>",
-        "_build": "<function ActorCriticPolicy._build at 0x7fed936be5e0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7fed936be670>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fed936be700>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fed936be790>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7fed936be820>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fed936be8b0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fed936be940>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fed936be9d0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7eff0fe724c0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7eff0fe72550>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7eff0fe725e0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7eff0fe72670>",
+        "_build": "<function ActorCriticPolicy._build at 0x7eff0fe72700>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7eff0fe72790>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7eff0fe72820>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7eff0fe728b0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7eff0fe72940>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7eff0fe729d0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7eff0fe72a60>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7eff0fe72af0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x7fed936b4b10>"
+        "_abc_impl": "<_abc_data object at 0x7eff0fe6aa50>"
     },
     "verbose": 0,
     "policy_kwargs": {},
@@ -43,44 +43,32 @@
         "_np_random": null
     },
     "n_envs": 1,
-    "num_timesteps": 100455,
-    "_total_timesteps": 100000,
+    "num_timesteps": 0,
+    "_total_timesteps": 0,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1676863652895088662,
-    "learning_rate": 0.4901809325786132,
+    "start_time": null,
+    "learning_rate": 0.0003,
     "tensorboard_log": null,
     "lr_schedule": {
         ":type:": "<class 'function'>",
-        ":serialized:": "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"
-    },
-    "_last_obs": {
-        ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAKZgn71U+Z4/DmX0vrQOJb+YjAQ/M7lmPwAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
-    },
-    "_last_episode_starts": {
-        ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+        ":serialized:": "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"
     },
+    "_last_obs": null,
+    "_last_episode_starts": null,
     "_last_original_obs": null,
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.004550000000000054,
-    "ep_info_buffer": {
-        ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
-    },
-    "ep_success_buffer": {
-        ":type:": "<class 'collections.deque'>",
-        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
-    },
-    "_n_updates": 1110,
-    "n_steps": 905,
-    "gamma": 0.000866430802601825,
-    "gae_lambda": 0.015423116225634408,
-    "ent_coef": 0.027609273631136383,
+    "_current_progress_remaining": 1,
+    "ep_info_buffer": null,
+    "ep_success_buffer": null,
+    "_n_updates": 0,
+    "n_steps": 1024,
+    "gamma": 0.99,
+    "gae_lambda": 0.95,
+    "ent_coef": 0.0,
     "vf_coef": 0.5,
     "max_grad_norm": 0.5,
     "batch_size": 64,

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0a844bf13a9b8680d2303f8a72510bde569d39ec7303903f70970815a689da8
-size 87929
+oid sha256:2497affac19a461e040f7a57c9a5933e93b10b5579b0a3d91d7d3978070520ec
+size 687

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63fda60986ad22bb7e46b7bc6fa497e45219663398ec8e46f2a2033a5c7dcadf
-size 43393
+oid sha256:43ba3babf10bd3835faef5229e21a948640f11e4dc5d113ac3ef4f95fd5e5773
+size 43265

ppo-LunarLander-v2/system_info.txt

@@ -2,6 +2,6 @@
 - Python: 3.8.10
 - Stable-Baselines3: 1.7.0
 - PyTorch: 1.13.1+cu116
-- GPU Enabled: True
+- GPU Enabled: False
 - Numpy: 1.21.6
 - Gym: 0.21.0

results.json

@@ -1 +1 @@
-{"mean_reward": -527.4464561101049, "std_reward": 131.56288311121673, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-20T03:32:56.788333"}
+{"mean_reward": -88.9957808105275, "std_reward": 41.1765105866572, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-20T11:31:49.497177"}