Upload PPO LunarLander-v2 trained agent 290
Browse files- README.md +1 -1
- config.json +1 -1
- ppo-LunarLander-v2.zip +2 -2
- ppo-LunarLander-v2/data +20 -20
- ppo-LunarLander-v2/policy.optimizer.pth +1 -1
- ppo-LunarLander-v2/policy.pth +1 -1
- replay.mp4 +0 -0
- results.json +1 -1
README.md
CHANGED
@@ -16,7 +16,7 @@ model-index:
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
-
value:
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: 291.50 +/- 19.57
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
config.json
CHANGED
@@ -1 +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 0x7f37ec9ac670>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f37ec9ac700>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f37ec9ac790>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f37ec9ac820>", "_build": "<function ActorCriticPolicy._build at 0x7f37ec9ac8b0>", "forward": "<function ActorCriticPolicy.forward at 0x7f37ec9ac940>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f37ec9ac9d0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f37ec9aca60>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f37ec9acaf0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f37ec9acb80>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f37ec9acc10>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f37ec9aa210>"}, "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": 1507328, "_total_timesteps": 1500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1670620719136546171, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_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": -0.004885333333333408, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 368, "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": "3.8.16", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu116", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
|
|
|
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 0x7ffa876b9ee0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ffa876b9f70>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ffa876bd040>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ffa876bd0d0>", "_build": "<function ActorCriticPolicy._build at 0x7ffa876bd160>", "forward": "<function ActorCriticPolicy.forward at 0x7ffa876bd1f0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ffa876bd280>", "_predict": "<function ActorCriticPolicy._predict at 0x7ffa876bd310>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ffa876bd3a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ffa876bd430>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ffa876bd4c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7ffa876b39c0>"}, "verbose": 2, "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": 1507328, "_total_timesteps": 1500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1670666246061433159, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_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": -0.004885333333333408, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVHRAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMI+8qD9FTzc0CUhpRSlIwBbJRLrowBdJRHQLC0roEjgQ91fZQoaAZoCWgPQwjbNoyC4OxvQJSGlFKUaBVLlWgWR0CwtLBhx5s1dX2UKGgGaAloD0MIH9YbtcLHckCUhpRSlGgVS6FoFkdAsLTLh0hePnV9lChoBmgJaA9DCBrerMF7DnJAlIaUUpRoFUuraBZHQLC0zYVqN6x1fZQoaAZoCWgPQwiQn41c91xyQJSGlFKUaBVLtWgWR0CwtNL6YVqOdX2UKGgGaAloD0MIV5OnrObockCUhpRSlGgVS8hoFkdAsLTV9Sde6nV9lChoBmgJaA9DCPs9sU6VAnRAlIaUUpRoFUvKaBZHQLC05nRLK3d1fZQoaAZoCWgPQwgdjxmozCRyQJSGlFKUaBVLq2gWR0CwtP5Mtbs4dX2UKGgGaAloD0MIPYBFfj0ickCUhpRSlGgVS65oFkdAsLUDUhFEzHV9lChoBmgJaA9DCAQ8aeGyHXJAlIaUUpRoFUu9aBZHQLC1D2OQyRB1fZQoaAZoCWgPQwhuxJPdzM1yQJSGlFKUaBVLmGgWR0CwtRxp5/smdX2UKGgGaAloD0MIur4PBwk4cUCUhpRSlGgVS7VoFkdAsLUyZRbbDnV9lChoBmgJaA9DCAJnKVmO73NAlIaUUpRoFUvFaBZHQLC1ORCx/ut1fZQoaAZoCWgPQwiKOQg62mhyQJSGlFKUaBVLl2gWR0CwtUrXDm8vdX2UKGgGaAloD0MIZoNMMjIZckCUhpRSlGgVS55oFkdAsLVLpPhybXV9lChoBmgJaA9DCA2nzM23uHFAlIaUUpRoFUutaBZHQLC1T3l0YCR1fZQoaAZoCWgPQwhxkBDlSwBwQJSGlFKUaBVLrGgWR0CwtVBsZYPodX2UKGgGaAloD0MIdO0L6MXdcUCUhpRSlGgVS4xoFkdAsLVi/Dcdo3V9lChoBmgJaA9DCFt5yf/kdnJAlIaUUpRoFUu6aBZHQLC1b3mmtQt1fZQoaAZoCWgPQwgKLev+8TpxQJSGlFKUaBVLpmgWR0CwtYFQIldDdX2UKGgGaAloD0MIIywq4jQkcUCUhpRSlGgVS6VoFkdAsLWS5wwTNHV9lChoBmgJaA9DCFPr/Ua7z3NAlIaUUpRoFUvHaBZHQLC1msVLzwt1fZQoaAZoCWgPQwjrVWR0gNNyQJSGlFKUaBVLyGgWR0CwtZ3rUsnRdX2UKGgGaAloD0MI0/iFV1IncUCUhpRSlGgVS55oFkdAsLW1MJx//nV9lChoBmgJaA9DCNwsXizM1XJAlIaUUpRoFUuyaBZHQLC1vyyUs4F1fZQoaAZoCWgPQwh2HD9UGpZyQJSGlFKUaBVLvGgWR0CwtcWAbyYpdX2UKGgGaAloD0MINZcbDLVNc0CUhpRSlGgVS8RoFkdAsLXt50KZ2XV9lChoBmgJaA9DCKncRC2ND3NAlIaUUpRoFUuzaBZHQLC1+ZdfLLZ1fZQoaAZoCWgPQwjluFM62OpzQJSGlFKUaBVLvmgWR0Cwtf7iADq4dX2UKGgGaAloD0MIIc1YNN0eckCUhpRSlGgVS61oFkdAsLYKARTS9nV9lChoBmgJaA9DCJdw6C2eiXBAlIaUUpRoFUuvaBZHQLC2CHlfZ291fZQoaAZoCWgPQwgV5dL4hYhzQJSGlFKUaBVLwGgWR0Cwth/IwM6SdX2UKGgGaAloD0MI1zOEYxbKckCUhpRSlGgVS7NoFkdAsLYl+DvmYHV9lChoBmgJaA9DCDZ1HhU/HnRAlIaUUpRoFUvWaBZHQLC2MSpzcRF1fZQoaAZoCWgPQwhkPEolvMtwQJSGlFKUaBVLtGgWR0CwtjQBYFJQdX2UKGgGaAloD0MIKEUr90KMcUCUhpRSlGgVS7hoFkdAsLZIpqh11XV9lChoBmgJaA9DCLqD2JnCSW9AlIaUUpRoFUudaBZHQLC2R+Pikwh1fZQoaAZoCWgPQwjoMjUJ3itzQJSGlFKUaBVLqmgWR0CwtksU/OdHdX2UKGgGaAloD0MIgLVq18Sgc0CUhpRSlGgVS6hoFkdAsLZQd8zAOHV9lChoBmgJaA9DCI55HXEIxHBAlIaUUpRoFUulaBZHQLC2bkBjnV51fZQoaAZoCWgPQwhWZHRAElRzQJSGlFKUaBVLvGgWR0Cwtn10Lc9GdX2UKGgGaAloD0MIEOZ2L/dqUECUhpRSlGgVS2NoFkdAsLaEoVmBfHV9lChoBmgJaA9DCIi7ehVZF3NAlIaUUpRoFUu4aBZHQLC2jMg2ZRd1fZQoaAZoCWgPQwirQgOxrBlyQJSGlFKUaBVLomgWR0CwtqATufEodX2UKGgGaAloD0MIlYEDWjqKcECUhpRSlGgVS6loFkdAsLa+q5sj3XV9lChoBmgJaA9DCNnMIanF+XFAlIaUUpRoFUu7aBZHQLC2xA1vVEx1fZQoaAZoCWgPQwjOiT20D95xQJSGlFKUaBVLsGgWR0CwtsgogFHKdX2UKGgGaAloD0MIwCZr1IOLckCUhpRSlGgVS41oFkdAsLbJ9mYjS3V9lChoBmgJaA9DCKWjHMwmnnNAlIaUUpRoFUvIaBZHQLC21yxzJZJ1fZQoaAZoCWgPQwi54XfTLQVyQJSGlFKUaBVLt2gWR0CwtupntfG/dX2UKGgGaAloD0MIXfkszwMjcUCUhpRSlGgVS51oFkdAsLb0cPvrnnV9lChoBmgJaA9DCEYMO4wJ1XFAlIaUUpRoFUvCaBZHQLC3A+i8Fpx1fZQoaAZoCWgPQwh0RL5LKb9xQJSGlFKUaBVLqWgWR0CwtwbyQPqcdX2UKGgGaAloD0MIXhPSGoPOc0CUhpRSlGgVS7poFkdAsLcQj9n9N3V9lChoBmgJaA9DCG6GG/B5i3NAlIaUUpRoFUvHaBZHQLC3HI3zcyp1fZQoaAZoCWgPQwi0qiUd5TlxQJSGlFKUaBVLt2gWR0CwtzQ/oq0/dX2UKGgGaAloD0MITtAmh09xcUCUhpRSlGgVS65oFkdAsLdBsl9jPXV9lChoBmgJaA9DCD+PUZ65eXJAlIaUUpRoFUu5aBZHQLC3RlyBCld1fZQoaAZoCWgPQwj8/s2LE2RxQJSGlFKUaBVLsGgWR0Cwt1hHTZxrdX2UKGgGaAloD0MIQgqeQm66c0CUhpRSlGgVS8hoFkdAsLdiuoxYaHV9lChoBmgJaA9DCCZV203wO3JAlIaUUpRoFUubaBZHQLC3bY51eSl1fZQoaAZoCWgPQwj6Dn7iQIJyQJSGlFKUaBVLr2gWR0Cwt30/r0J4dX2UKGgGaAloD0MItybdlsgockCUhpRSlGgVS7doFkdAsLeAohIOH3V9lChoBmgJaA9DCAVu3c0TGXNAlIaUUpRoFUuvaBZHQLC3j/6frbB1fZQoaAZoCWgPQwgX1o13R+tzQJSGlFKUaBVL1GgWR0Cwt6skhRqHdX2UKGgGaAloD0MIfgIoRhbpckCUhpRSlGgVS8RoFkdAsLfAaef7JnV9lChoBmgJaA9DCN/8hokGtHJAlIaUUpRoFUuwaBZHQLC3xgflp491fZQoaAZoCWgPQwhK7xtfe/JwQJSGlFKUaBVLwGgWR0Cwt8hD9fkWdX2UKGgGaAloD0MIQYAMHTsXdECUhpRSlGgVS6poFkdAsLfNvIfbK3V9lChoBmgJaA9DCNzz/GljAHJAlIaUUpRoFUuiaBZHQLC30lTFVDN1fZQoaAZoCWgPQwhhNZawtgF0QJSGlFKUaBVLrGgWR0CwuAg4KhL5dX2UKGgGaAloD0MILH3ognoVckCUhpRSlGgVS7xoFkdAsLgXAUL2H3V9lChoBmgJaA9DCJgYy/TLGXFAlIaUUpRoFUupaBZHQLC4I+wkgOl1fZQoaAZoCWgPQwjbbReaq6tzQJSGlFKUaBVL0WgWR0CwuCJLVWjodX2UKGgGaAloD0MImfT3UjgPdECUhpRSlGgVS8VoFkdAsLg5ZGKAKHV9lChoBmgJaA9DCDOID+z4bnNAlIaUUpRoFUuzaBZHQLC4TMOPNml1fZQoaAZoCWgPQwhD5zV2CdFyQJSGlFKUaBVLvmgWR0CwuF296C17dX2UKGgGaAloD0MI8BZIUHz2c0CUhpRSlGgVS9JoFkdAsLhgg5imVXV9lChoBmgJaA9DCINPc/Lig3FAlIaUUpRoFUuoaBZHQLC4b2H+Idl1fZQoaAZoCWgPQwgy5UNQtfxuQJSGlFKUaBVLnWgWR0CwuHa19fCzdX2UKGgGaAloD0MIqfV+o502ckCUhpRSlGgVS8poFkdAsLh8aMrEtXV9lChoBmgJaA9DCIXP1sEBy3BAlIaUUpRoFUu6aBZHQLC4nmzByjp1fZQoaAZoCWgPQwjIe9XKhERvQJSGlFKUaBVLsmgWR0CwuJ/kRzzVdX2UKGgGaAloD0MI2gHXFfNDc0CUhpRSlGgVS8xoFkdAsLi4RJ2+wnV9lChoBmgJaA9DCEQxeQNMZ3NAlIaUUpRoFUvcaBZHQLC4w1bJOnF1fZQoaAZoCWgPQwg8oGzKFT5yQJSGlFKUaBVLt2gWR0CwuN3V5KODdX2UKGgGaAloD0MIswdagSF5c0CUhpRSlGgVS6NoFkdAsLjfCj1wpHV9lChoBmgJaA9DCLxdL02R/HBAlIaUUpRoFUulaBZHQLC440Nz8xd1fZQoaAZoCWgPQwgMdy6MNENxQJSGlFKUaBVLsmgWR0CwuOWkSElFdX2UKGgGaAloD0MIucfSh24fckCUhpRSlGgVS6ZoFkdAsLkeCyyD7XV9lChoBmgJaA9DCD6WPnSBlXFAlIaUUpRoFUu2aBZHQLC5HcEeQuF1fZQoaAZoCWgPQwgVVFT9SjxvQJSGlFKUaBVLomgWR0CwuTCJO32FdX2UKGgGaAloD0MIhZSfVLuuc0CUhpRSlGgVS9loFkdAsLk0Q/X5FnV9lChoBmgJaA9DCKXap+PxG3NAlIaUUpRoFUvEaBZHQLC5Pxy4nWt1fZQoaAZoCWgPQwgN/n4xW4xzQJSGlFKUaBVLzGgWR0CwuVj+rELqdX2UKGgGaAloD0MIV7H4TeHHcECUhpRSlGgVS6JoFkdAsLlX1wo9cXV9lChoBmgJaA9DCEw0SMGT/HNAlIaUUpRoFUvRaBZHQLC5aonKGL11fZQoaAZoCWgPQwgnZr0YSkByQJSGlFKUaBVLsGgWR0CwuWhESdvsdX2UKGgGaAloD0MISgosgGnzc0CUhpRSlGgVS7NoFkdAsLmCv0RODnV9lChoBmgJaA9DCBpqFJLMNHNAlIaUUpRoFUuqaBZHQLC5g8+zMRp1ZS4="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 1840, "n_steps": 2048, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 256, "n_epochs": 8, "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-LunarLander-v2.zip
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:abf7ed9a131bbda45ad3c2b57a5a0d525433098643073847686b47484a6f4336
|
3 |
+
size 147088
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,21 +4,21 @@
|
|
4 |
":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
5 |
"__module__": "stable_baselines3.common.policies",
|
6 |
"__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 ",
|
7 |
-
"__init__": "<function ActorCriticPolicy.__init__ at
|
8 |
-
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at
|
9 |
-
"reset_noise": "<function ActorCriticPolicy.reset_noise at
|
10 |
-
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at
|
11 |
-
"_build": "<function ActorCriticPolicy._build at
|
12 |
-
"forward": "<function ActorCriticPolicy.forward at
|
13 |
-
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at
|
14 |
-
"_predict": "<function ActorCriticPolicy._predict at
|
15 |
-
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at
|
16 |
-
"get_distribution": "<function ActorCriticPolicy.get_distribution at
|
17 |
-
"predict_values": "<function ActorCriticPolicy.predict_values at
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
-
"_abc_impl": "<_abc_data object at
|
20 |
},
|
21 |
-
"verbose":
|
22 |
"policy_kwargs": {},
|
23 |
"observation_space": {
|
24 |
":type:": "<class 'gym.spaces.box.Box'>",
|
@@ -47,7 +47,7 @@
|
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
-
"start_time":
|
51 |
"learning_rate": 0.0003,
|
52 |
"tensorboard_log": null,
|
53 |
"lr_schedule": {
|
@@ -56,7 +56,7 @@
|
|
56 |
},
|
57 |
"_last_obs": {
|
58 |
":type:": "<class 'numpy.ndarray'>",
|
59 |
-
":serialized:": "
|
60 |
},
|
61 |
"_last_episode_starts": {
|
62 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -69,21 +69,21 @@
|
|
69 |
"_current_progress_remaining": -0.004885333333333408,
|
70 |
"ep_info_buffer": {
|
71 |
":type:": "<class 'collections.deque'>",
|
72 |
-
":serialized:": "
|
73 |
},
|
74 |
"ep_success_buffer": {
|
75 |
":type:": "<class 'collections.deque'>",
|
76 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
},
|
78 |
-
"_n_updates":
|
79 |
-
"n_steps":
|
80 |
"gamma": 0.999,
|
81 |
"gae_lambda": 0.98,
|
82 |
"ent_coef": 0.01,
|
83 |
"vf_coef": 0.5,
|
84 |
"max_grad_norm": 0.5,
|
85 |
-
"batch_size":
|
86 |
-
"n_epochs":
|
87 |
"clip_range": {
|
88 |
":type:": "<class 'function'>",
|
89 |
":serialized:": "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"
|
|
|
4 |
":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
5 |
"__module__": "stable_baselines3.common.policies",
|
6 |
"__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 ",
|
7 |
+
"__init__": "<function ActorCriticPolicy.__init__ at 0x7ffa876b9ee0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ffa876b9f70>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ffa876bd040>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ffa876bd0d0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7ffa876bd160>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7ffa876bd1f0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ffa876bd280>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7ffa876bd310>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ffa876bd3a0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ffa876bd430>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7ffa876bd4c0>",
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7ffa876b39c0>"
|
20 |
},
|
21 |
+
"verbose": 2,
|
22 |
"policy_kwargs": {},
|
23 |
"observation_space": {
|
24 |
":type:": "<class 'gym.spaces.box.Box'>",
|
|
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
+
"start_time": 1670666246061433159,
|
51 |
"learning_rate": 0.0003,
|
52 |
"tensorboard_log": null,
|
53 |
"lr_schedule": {
|
|
|
56 |
},
|
57 |
"_last_obs": {
|
58 |
":type:": "<class 'numpy.ndarray'>",
|
59 |
+
":serialized:": "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"
|
60 |
},
|
61 |
"_last_episode_starts": {
|
62 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
69 |
"_current_progress_remaining": -0.004885333333333408,
|
70 |
"ep_info_buffer": {
|
71 |
":type:": "<class 'collections.deque'>",
|
72 |
+
":serialized:": "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"
|
73 |
},
|
74 |
"ep_success_buffer": {
|
75 |
":type:": "<class 'collections.deque'>",
|
76 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
},
|
78 |
+
"_n_updates": 1840,
|
79 |
+
"n_steps": 2048,
|
80 |
"gamma": 0.999,
|
81 |
"gae_lambda": 0.98,
|
82 |
"ent_coef": 0.01,
|
83 |
"vf_coef": 0.5,
|
84 |
"max_grad_norm": 0.5,
|
85 |
+
"batch_size": 256,
|
86 |
+
"n_epochs": 8,
|
87 |
"clip_range": {
|
88 |
":type:": "<class 'function'>",
|
89 |
":serialized:": "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"
|
ppo-LunarLander-v2/policy.optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 87929
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77ec1c24ace72f4c694a3426cd410ea70a0b47fe529be1ba3232aee9acfdf6d2
|
3 |
size 87929
|
ppo-LunarLander-v2/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43201
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60840f02591ea5df2f4e6c696c52f5b06a05d84826683cb5bdca5ea7bb356a22
|
3 |
size 43201
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 291.499168630996, "std_reward": 19.568092765718927, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-10T10:18:29.262731"}
|