Upload PPO LunarLander-v2 trained agent
Browse files- README.md +1 -1
- config.json +1 -1
- ppo-LunarLander-v2.zip +2 -2
- ppo-LunarLander-v2/data +22 -22
- 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: 279.21 +/- 11.68
|
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 0x17ee62b90>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x17ee62c20>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x17ee62cb0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x17ee62d40>", "_build": "<function ActorCriticPolicy._build at 0x17ee62dd0>", "forward": "<function ActorCriticPolicy.forward at 0x17ee62e60>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x17ee62ef0>", "_predict": "<function ActorCriticPolicy._predict at 0x17ee62f80>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x17ee63010>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x17ee630a0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x17ee63130>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x17ee70f40>"}, "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:": "gAWViAAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 2015232, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1679517932.291308, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVlwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMZS9vcHQvaG9tZWJyZXcvQ2Fza3Jvb20vbWFtYmFmb3JnZS9iYXNlL2xpYi9weXRob24zLjEwL3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCBAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flGgMdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpSMHGNsb3VkcGlja2xlLmNsb3VkcGlja2xlX2Zhc3SUjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoHn2UfZQoaBZoDYwMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBeMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHPzOpKjBVMmGFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="}, "_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": -0.007616000000000067, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 492, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.99, "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": "macOS-13.2.1-arm64-arm-64bit Darwin Kernel Version 22.3.0: Mon Jan 30 20:38:37 PST 2023; root:xnu-8792.81.3~2/RELEASE_ARM64_T6000", "Python": "3.10.9", "Stable-Baselines3": "1.5.0", "PyTorch": "1.13.1", "GPU Enabled": "False", "Numpy": "1.22.4", "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 0x2901ceb90>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x2901cec20>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x2901cecb0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x2901ced40>", "_build": "<function ActorCriticPolicy._build at 0x2901cedd0>", "forward": "<function ActorCriticPolicy.forward at 0x2901cee60>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x2901ceef0>", "_predict": "<function ActorCriticPolicy._predict at 0x2901cef80>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x2901cf010>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x2901cf0a0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x2901cf130>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x2901c6100>"}, "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": 10010624, "_total_timesteps": 10000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1679539101.9133031, "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": -0.0010623999999999079, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVHhAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMI0NA/wcWcckCUhpRSlIwBbJRLrowBdJRHQKcHJT6zmfZ1fZQoaAZoCWgPQwiuKvuuSO1xQJSGlFKUaBVLsGgWR0CnByvnjhkzdX2UKGgGaAloD0MINdQoJNkJckCUhpRSlGgVS6poFkdApwdASWZ7X3V9lChoBmgJaA9DCHjUmBAzr3FAlIaUUpRoFUu3aBZHQKcHSwQlKK51fZQoaAZoCWgPQwgmVHB4gWdzQJSGlFKUaBVLyWgWR0CnB041P3zudX2UKGgGaAloD0MIu7iNBjBMckCUhpRSlGgVS81oFkdApwdYO8TSLXV9lChoBmgJaA9DCBq/8EqSCHJAlIaUUpRoFUvMaBZHQKcHXwc5sCV1fZQoaAZoCWgPQwiFlnX/mLNxQJSGlFKUaBVLsmgWR0CnB2ZOzposdX2UKGgGaAloD0MI0sd8QOBzc0CUhpRSlGgVS8NoFkdApwd3LaEi+3V9lChoBmgJaA9DCHIYzF8hQnFAlIaUUpRoFUuoaBZHQKcHgdpZfUp1fZQoaAZoCWgPQwj7Wpca4QRwQJSGlFKUaBVLw2gWR0CnB5DnvDxcdX2UKGgGaAloD0MI/aTap2PFckCUhpRSlGgVS8xoFkdApwe1ALRa5nV9lChoBmgJaA9DCNZ0PdG1lHFAlIaUUpRoFUvCaBZHQKcH0uwHJLd1fZQoaAZoCWgPQwg6kPXUKtNwQJSGlFKUaBVLrmgWR0CnB9v8AJb/dX2UKGgGaAloD0MIADrMl1c+ckCUhpRSlGgVS6VoFkdApwqhJGvwE3V9lChoBmgJaA9DCGx6UFAKV3JAlIaUUpRoFUvOaBZHQKcKrY0VJtl1fZQoaAZoCWgPQwgsLSP13i9zQJSGlFKUaBVLpWgWR0CnCrkY4yXVdX2UKGgGaAloD0MIxhhYx7EJcUCUhpRSlGgVS8VoFkdApwq//R3NcHV9lChoBmgJaA9DCGaFIt1PtnFAlIaUUpRoFUukaBZHQKcK2Hpr1ul1fZQoaAZoCWgPQwizeRwGM85wQJSGlFKUaBVLlWgWR0CnCuNipeeGdX2UKGgGaAloD0MIY7Mj1ffpc0CUhpRSlGgVS7ZoFkdApwrlX1anrXV9lChoBmgJaA9DCJ2BkZf1nnBAlIaUUpRoFUvIaBZHQKcK67QLNOd1fZQoaAZoCWgPQwhgdk8elg9zQJSGlFKUaBVLzWgWR0CnCvQBgeA/dX2UKGgGaAloD0MIipElc6wtcUCUhpRSlGgVS75oFkdApwr8+u/1x3V9lChoBmgJaA9DCKJESx7PZHRAlIaUUpRoFUutaBZHQKcLFng5zYF1fZQoaAZoCWgPQwj/d0SF6r5yQJSGlFKUaBVL4mgWR0CnC0cf3evZdX2UKGgGaAloD0MIyCb5EX/XcECUhpRSlGgVS9BoFkdApwtstNBWxXV9lChoBmgJaA9DCLK8qx4wtnBAlIaUUpRoFUuuaBZHQKcLcR+SbH91fZQoaAZoCWgPQwiQhegQeGhyQJSGlFKUaBVLsGgWR0CnC4GgrYoRdX2UKGgGaAloD0MIWFnbFI/cckCUhpRSlGgVS89oFkdApwuOVHFxXHV9lChoBmgJaA9DCIP6ljldripAlIaUUpRoFUtjaBZHQKcLma3I+4d1fZQoaAZoCWgPQwgJpS+EHPNzQJSGlFKUaBVL1mgWR0CnC6H2h7E6dX2UKGgGaAloD0MIol9bP31Wc0CUhpRSlGgVS79oFkdApwujGLk0anV9lChoBmgJaA9DCEz/klQm1XFAlIaUUpRoFUu9aBZHQKcLp9wWFex1fZQoaAZoCWgPQwhSKAtfHw9yQJSGlFKUaBVLtWgWR0CnC7f6O5rhdX2UKGgGaAloD0MIqrUwC+28bkCUhpRSlGgVS69oFkdApwvEafjCHnV9lChoBmgJaA9DCPllMEakGXNAlIaUUpRoFUvEaBZHQKcL1qAz5451fZQoaAZoCWgPQwgdOj3vxodyQJSGlFKUaBVLzGgWR0CnC95PVNHpdX2UKGgGaAloD0MIIR6Jl+dPckCUhpRSlGgVS8ZoFkdApwvovBacJHV9lChoBmgJaA9DCORNfotOEnNAlIaUUpRoFUvPaBZHQKcL/XxvvSd1fZQoaAZoCWgPQwh3EhH+he1wQJSGlFKUaBVLpmgWR0CnDFIOhCdCdX2UKGgGaAloD0MInznrU84ZdECUhpRSlGgVS9FoFkdApwxUGzKLbnV9lChoBmgJaA9DCMbdIFqrc3NAlIaUUpRoFUu8aBZHQKcMXHYpUgl1fZQoaAZoCWgPQwgsKXefIyhwQJSGlFKUaBVLw2gWR0CnDGq28Zk1dX2UKGgGaAloD0MI5KHvbqWUc0CUhpRSlGgVS75oFkdApwyAwwj+rHV9lChoBmgJaA9DCKsmiLqP0nJAlIaUUpRoFUu8aBZHQKcMmckt29t1fZQoaAZoCWgPQwgQecvVD0BzQJSGlFKUaBVLsWgWR0CnDK6V2Rq5dX2UKGgGaAloD0MI7KLogc8qdECUhpRSlGgVS9ZoFkdApwywSFoL5XV9lChoBmgJaA9DCA7ZQLpYQHJAlIaUUpRoFUvPaBZHQKcMsHRCx/x1fZQoaAZoCWgPQwhK7rCJzO9xQJSGlFKUaBVLv2gWR0CnDLOXmeUZdX2UKGgGaAloD0MI41Eq4ckycUCUhpRSlGgVS6loFkdApwzAxk/bCnV9lChoBmgJaA9DCNJUT+YfO3JAlIaUUpRoFUuVaBZHQKcMycTakAR1fZQoaAZoCWgPQwjqPgCpDfNyQJSGlFKUaBVLwWgWR0CnDNdq1w5vdX2UKGgGaAloD0MILIApA4eQc0CUhpRSlGgVS/loFkdApwzkPczqKXV9lChoBmgJaA9DCPWDukihSXNAlIaUUpRoFUu8aBZHQKcM5CNS6191fZQoaAZoCWgPQwhpdAexM79wQJSGlFKUaBVLrWgWR0CnDTce8wpOdX2UKGgGaAloD0MIhQg4hKrzckCUhpRSlGgVS89oFkdApw1uwRoRI3V9lChoBmgJaA9DCFbYDHBBUHNAlIaUUpRoFUvHaBZHQKcNcdU83dd1fZQoaAZoCWgPQwiVnuklRpdwQJSGlFKUaBVLwGgWR0CnDX704BFNdX2UKGgGaAloD0MIEW+df7vFcUCUhpRSlGgVS69oFkdApw2ACZF5OnV9lChoBmgJaA9DCMg/M4iPBHFAlIaUUpRoFUujaBZHQKcNhAzpHI91fZQoaAZoCWgPQwhHy4Eeqn1zQJSGlFKUaBVL6mgWR0CnDYsQd0aIdX2UKGgGaAloD0MI7RD/sKUjdECUhpRSlGgVS7JoFkdApw2Wr4nF53V9lChoBmgJaA9DCEZda+9TZnFAlIaUUpRoFUu+aBZHQKcNpBAv+Ox1fZQoaAZoCWgPQwibjgBulkVzQJSGlFKUaBVLvGgWR0CnDaWNvOyFdX2UKGgGaAloD0MI7Q2+MBn+ckCUhpRSlGgVS79oFkdApw20MqjJuHV9lChoBmgJaA9DCNwpHaz/gXBAlIaUUpRoFUu4aBZHQKcNv+y7f511fZQoaAZoCWgPQwgVHF4QUVtxQJSGlFKUaBVLsmgWR0CnDcWRJVbSdX2UKGgGaAloD0MIZAW/DTHacECUhpRSlGgVS8hoFkdApw3GkJrtV3V9lChoBmgJaA9DCBLeHoQAxXNAlIaUUpRoFUu+aBZHQKcN0cYIjW11fZQoaAZoCWgPQwh7Lei98R5yQJSGlFKUaBVLuWgWR0CnDha7VawEdX2UKGgGaAloD0MI4gLQKF16cUCUhpRSlGgVS5toFkdApw4l6JIlMXV9lChoBmgJaA9DCMXFUbkJdmhAlIaUUpRoFU3oA2gWR0CnDiil7+kydX2UKGgGaAloD0MIll8GY8SXckCUhpRSlGgVS6BoFkdApw4p+UhV2nV9lChoBmgJaA9DCJjaUgc5m3BAlIaUUpRoFUuaaBZHQKcOMEEkjX51fZQoaAZoCWgPQwjRsYNKXHVPQJSGlFKUaBVLgmgWR0CnDjV63RXwdX2UKGgGaAloD0MIEVSNXg2ncECUhpRSlGgVS6RoFkdApw48m2LHdXV9lChoBmgJaA9DCGGm7V9ZNnFAlIaUUpRoFUuYaBZHQKcOSwZflZJ1fZQoaAZoCWgPQwhj0AmhwwVxQJSGlFKUaBVLumgWR0CnDlbF0gbIdX2UKGgGaAloD0MIGqTgKeT3cUCUhpRSlGgVS7FoFkdApw5XpdKNAHV9lChoBmgJaA9DCHHIBtLFPVlAlIaUUpRoFUuZaBZHQKcOWSqU/wB1fZQoaAZoCWgPQwiFlnX/GKhzQJSGlFKUaBVLymgWR0CnDl3tShrWdX2UKGgGaAloD0MIwCFUqRk3c0CUhpRSlGgVS7BoFkdApw57spoboHV9lChoBmgJaA9DCLBXWHC/+W9AlIaUUpRoFUu0aBZHQKcOjSaVlf91fZQoaAZoCWgPQwjjNEQVvpFyQJSGlFKUaBVLxmgWR0CnDpVXmvGIdX2UKGgGaAloD0MIMXkDzPwPc0CUhpRSlGgVS9poFkdApw6k8eS0SnV9lChoBmgJaA9DCKs+V1vxNXBAlIaUUpRoFUu2aBZHQKcO1cRDkU91fZQoaAZoCWgPQwgxlX7CWVhwQJSGlFKUaBVLnmgWR0CnDtfmDDjzdX2UKGgGaAloD0MI8tJNYtCWcECUhpRSlGgVS7VoFkdApw7ii0v4/XV9lChoBmgJaA9DCEOPGD237nFAlIaUUpRoFUuwaBZHQKcO53AVO9F1fZQoaAZoCWgPQwhJZvUOt/VwQJSGlFKUaBVLuGgWR0CnDuh6By0bdX2UKGgGaAloD0MI5L7VOjH0ckCUhpRSlGgVS8loFkdApw76g9Net3V9lChoBmgJaA9DCOwzZ32KaXFAlIaUUpRoFUu6aBZHQKcO/tOVPep1fZQoaAZoCWgPQwjb+BOVTRZyQJSGlFKUaBVLtWgWR0CnDwkvsZ5zdX2UKGgGaAloD0MIfjuJCL9Lc0CUhpRSlGgVS71oFkdApw8d8ma6SXV9lChoBmgJaA9DCCJPkq5Z53FAlIaUUpRoFUu5aBZHQKcPIciGFi91fZQoaAZoCWgPQwh+p8mMN4dzQJSGlFKUaBVLyWgWR0CnDytjkMkQdX2UKGgGaAloD0MISFM9mX+mb0CUhpRSlGgVS6RoFkdApw8u5nUUf3V9lChoBmgJaA9DCCr+74iKenNAlIaUUpRoFUvLaBZHQKcPL5WzWwx1fZQoaAZoCWgPQwjMDBtl/ShyQJSGlFKUaBVLvWgWR0CnD1hrWRRudWUu"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 2444, "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": "macOS-13.2.1-arm64-arm-64bit Darwin Kernel Version 22.3.0: Mon Jan 30 20:38:37 PST 2023; root:xnu-8792.81.3~2/RELEASE_ARM64_T6000", "Python": "3.10.9", "Stable-Baselines3": "1.5.0", "PyTorch": "1.13.1", "GPU Enabled": "False", "Numpy": "1.22.4", "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 sha256:0cb939ad9dc2607f2fdfddbf494f7c1859c6ae5429febc0ec0234ae456269c92
|
3 |
+
size 146417
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,25 +4,25 @@
|
|
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._abc_data object at
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
23 |
"observation_space": {
|
24 |
":type:": "<class 'gym.spaces.box.Box'>",
|
25 |
-
":serialized:": "
|
26 |
"dtype": "float32",
|
27 |
"_shape": [
|
28 |
8
|
@@ -35,19 +35,19 @@
|
|
35 |
},
|
36 |
"action_space": {
|
37 |
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
38 |
-
":serialized:": "
|
39 |
"n": 4,
|
40 |
"_shape": [],
|
41 |
"dtype": "int64",
|
42 |
"_np_random": null
|
43 |
},
|
44 |
"n_envs": 16,
|
45 |
-
"num_timesteps":
|
46 |
-
"_total_timesteps":
|
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'>",
|
@@ -66,19 +66,19 @@
|
|
66 |
"_episode_num": 0,
|
67 |
"use_sde": false,
|
68 |
"sde_sample_freq": -1,
|
69 |
-
"_current_progress_remaining": -0.
|
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": 1024,
|
80 |
"gamma": 0.999,
|
81 |
-
"gae_lambda": 0.
|
82 |
"ent_coef": 0.01,
|
83 |
"vf_coef": 0.5,
|
84 |
"max_grad_norm": 0.5,
|
|
|
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 0x2901ceb90>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x2901cec20>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x2901cecb0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x2901ced40>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x2901cedd0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x2901cee60>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x2901ceef0>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x2901cef80>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x2901cf010>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x2901cf0a0>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x2901cf130>",
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc._abc_data object at 0x2901c6100>"
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
23 |
"observation_space": {
|
24 |
":type:": "<class 'gym.spaces.box.Box'>",
|
25 |
+
":serialized:": "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",
|
26 |
"dtype": "float32",
|
27 |
"_shape": [
|
28 |
8
|
|
|
35 |
},
|
36 |
"action_space": {
|
37 |
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
38 |
+
":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
39 |
"n": 4,
|
40 |
"_shape": [],
|
41 |
"dtype": "int64",
|
42 |
"_np_random": null
|
43 |
},
|
44 |
"n_envs": 16,
|
45 |
+
"num_timesteps": 10010624,
|
46 |
+
"_total_timesteps": 10000000,
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
+
"start_time": 1679539101.9133031,
|
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'>",
|
|
|
66 |
"_episode_num": 0,
|
67 |
"use_sde": false,
|
68 |
"sde_sample_freq": -1,
|
69 |
+
"_current_progress_remaining": -0.0010623999999999079,
|
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": 2444,
|
79 |
"n_steps": 1024,
|
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,
|
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 87545
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:849d62dceeb23d50825f6e25021531a86c6c8f4d0bb445ac350cd70a22c6522f
|
3 |
size 87545
|
ppo-LunarLander-v2/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43073
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb831cf90c88c9b0e14df752aace34262a20ed2174ad177f1062e95495e16bc5
|
3 |
size 43073
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 279.21314713334147, "std_reward": 11.67965226754592, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-22T23:27:38.411707"}
|