Commit
•
e9dab1f
1
Parent(s):
b203580
Upload PPO LunarLander-v2 trained agent
Browse files- README.md +4 -4
- config.json +1 -1
- ppo-LunarLander-v2.zip +2 -2
- ppo-LunarLander-v2/data +21 -21
- 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
@@ -6,7 +6,7 @@ tags:
|
|
6 |
- reinforcement-learning
|
7 |
- stable-baselines3
|
8 |
model-index:
|
9 |
-
- name:
|
10 |
results:
|
11 |
- task:
|
12 |
type: reinforcement-learning
|
@@ -16,13 +16,13 @@ model-index:
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
-
value:
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
23 |
|
24 |
-
# **
|
25 |
-
This is a trained model of a **
|
26 |
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
27 |
|
28 |
## Usage (with Stable-baselines3)
|
|
|
6 |
- reinforcement-learning
|
7 |
- stable-baselines3
|
8 |
model-index:
|
9 |
+
- name: DQN
|
10 |
results:
|
11 |
- task:
|
12 |
type: reinforcement-learning
|
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: 298.82 +/- 9.47
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
23 |
|
24 |
+
# **DQN** Agent playing **LunarLander-v2**
|
25 |
+
This is a trained model of a **DQN** agent playing **LunarLander-v2**
|
26 |
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
27 |
|
28 |
## Usage (with Stable-baselines3)
|
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 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 0x7e7ac8c8d240>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7e7ac8c8d2d0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7e7ac8c8d360>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7e7ac8c8d3f0>", "_build": "<function ActorCriticPolicy._build at 0x7e7ac8c8d480>", "forward": "<function ActorCriticPolicy.forward at 0x7e7ac8c8d510>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7e7ac8c8d5a0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7e7ac8c8d630>", "_predict": "<function ActorCriticPolicy._predict at 0x7e7ac8c8d6c0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7e7ac8c8d750>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7e7ac8c8d7e0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7e7ac8c8d870>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7e7ac8c7f540>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1690271081592478000, "learning_rate": 0.0003, "tensorboard_log": null, "_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": -0.015808000000000044, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 248, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True True True True True True]", "bounded_above": "[ True True True True True True True True]", "_shape": [8], "low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "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, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 UTC 2023", "Python": "3.10.6", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
|
|
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 0x7d9684cbaef0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d9684cbaf80>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d9684cbb010>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d9684cbb0a0>", "_build": "<function ActorCriticPolicy._build at 0x7d9684cbb130>", "forward": "<function ActorCriticPolicy.forward at 0x7d9684cbb1c0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d9684cbb250>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d9684cbb2e0>", "_predict": "<function ActorCriticPolicy._predict at 0x7d9684cbb370>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d9684cbb400>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d9684cbb490>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d9684cbb520>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7d9684cc4bc0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 2015232, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1690341353196836452, "learning_rate": 0.0003, "tensorboard_log": null, "_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, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWV5AsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQHHNEZJkGzOMAWyUS9eMAXSUR0CuadrYPGyYdX2UKGgGR0BwmYjqv/zbaAdL5mgIR0Cuaj5FPSDzdX2UKGgGR0BwinqfOD8MaAdLxGgIR0Cuak0DU3GXdX2UKGgGR0BynZlAeJYUaAdLwGgIR0Cuarh0p3HJdX2UKGgGR0BzDl/hESdwaAdL5WgIR0CuatTTWoWIdX2UKGgGR0BydCee4Cp4aAdL+2gIR0CuawbpV0cPdX2UKGgGR0BxeB3Qla8paAdLw2gIR0CuazLp7kXDdX2UKGgGR0Bv3Q2Kl54XaAdLzmgIR0Cua92Rq46PdX2UKGgGR0ByX0b5uZTiaAdL0WgIR0CubIA6ltTDdX2UKGgGR0BxjwiGFi8WaAdLwWgIR0CubIElVtGedX2UKGgGR0BxL9MK1G9YaAdL1mgIR0CubKG8dxQ0dX2UKGgGR0Bw9XJ4jbBXaAdL2WgIR0CubNTdk8RudX2UKGgGR0BvlzAJswcpaAdLymgIR0CubSOZTho/dX2UKGgGR0Bz2AQbuMMraAdL6WgIR0CubalgDzRQdX2UKGgGR0BzojcZccENaAdLxGgIR0CubcunMt9QdX2UKGgGR0Bykcc81XNkaAdL7GgIR0CubhZVn27GdX2UKGgGR0ByG1NUOuq4aAdLv2gIR0CubimnO0LMdX2UKGgGR0Bw6AornTy8aAdLxmgIR0Cubi+SKWLQdX2UKGgGR0BxCkn4O+ZgaAdL0GgIR0CubpL9VFQVdX2UKGgGR0By1lntfG+9aAdLy2gIR0CubqCml67edX2UKGgGR0Bo3wf6oESvaAdN6ANoCEdArm76Tnq3VnV9lChoBkdAcDqipvP1MGgHS9VoCEdArm85SNwR5HV9lChoBkdAccCq8lHBlGgHS8xoCEdArm+HEbYK6XV9lChoBkdAcfVhcJMQE2gHS71oCEdArm+e2LHdXXV9lChoBkdAcTlXNke6qmgHS9hoCEdArm+yeVcD83V9lChoBkdAcTVGfPHDJmgHS+hoCEdArnAG16Vt43V9lChoBkdAcD0f6XSjQGgHS8xoCEdArnAqoKlYU3V9lChoBkdAcWkEfkmx+2gHS7BoCEdAroI+Hk92YHV9lChoBkdAc+tPdl/YrmgHS9xoCEdAroJ19ORDC3V9lChoBkdAcSZzru6VdGgHS9poCEdAroKcU/OdG3V9lChoBkdAcAyd2gWadGgHS8hoCEdAroKnkkrwv3V9lChoBkdAcj38rZrYXmgHS9ZoCEdAroMLfm9xqHV9lChoBkdAbfF56dDpkmgHS8loCEdAroNMlJHy3HV9lChoBkdAcke3g1m8NGgHS9FoCEdAroOJUFSsKnV9lChoBkdAb2lww0wai2gHS79oCEdAroOeXRgJC3V9lChoBkdAb5TmGM4tH2gHS8toCEdAroRJzHS4OXV9lChoBkdActerAP/aQGgHS71oCEdAroRmARTS9nV9lChoBkdAc0AsJIDoyWgHS+hoCEdAroV0SCe2/nV9lChoBkdAcinlWfbsW2gHS8xoCEdAroWxClabF3V9lChoBkdAcYeu8scyWWgHS95oCEdAroXn6VMVUXV9lChoBkdAcO40Jng5zmgHS7ZoCEdAroaBv3rUsnV9lChoBkdAckD72+PBBWgHS7toCEdAroaOR3eN1nV9lChoBkdAcP4ohpxm02gHS9ZoCEdAroaxFuvU0HV9lChoBkdAcnAMQEpy62gHS7NoCEdArobBWYF7lnV9lChoBkdAc0m8zQ/oq2gHS9poCEdAroblB0IToXV9lChoBkdAcpqMtbs4UGgHS75oCEdArocYk/r0KHV9lChoBkdAcYN6+36RAGgHS7poCEdArocxSBK+SXV9lChoBkdAcpAxe9i+c2gHS79oCEdArodRTMqz7nV9lChoBkdAcvmCGetjkWgHS8FoCEdArofQUHpr13V9lChoBkdAc3LZHd43WGgHS85oCEdArofuaKDTSnV9lChoBkdAcIZ8CxNZeWgHS71oCEdAroh/1QIldHV9lChoBkdAaAj2YfGMoGgHTegDaAhHQK6I1y0a6z51fZQoaAZHQHEJx+4LCvZoB0vPaAhHQK6I7amoBJZ1fZQoaAZHQHHf0Wl/H5toB0vUaAhHQK6JG9ZA6dV1fZQoaAZHQHCTFIZqEe1oB0u+aAhHQK6JaTr3TNN1fZQoaAZHQHCoEoOQQtloB0u/aAhHQK6JflkpZwJ1fZQoaAZHQG7guSOinHhoB0u1aAhHQK6Jfm+TNdJ1fZQoaAZHQHGPSqQzUI9oB0vSaAhHQK6JkPwNLDh1fZQoaAZHQG//XcHnln1oB0vWaAhHQK6JlKYiPhh1fZQoaAZHQG7KWM85jpdoB0vLaAhHQK6J/tmcvuh1fZQoaAZHQHBawcPvrnloB0vUaAhHQK6KOuuA7Pp1fZQoaAZHQHGg0jX4CZFoB0vaaAhHQK6KdIRywOh1fZQoaAZHQHHAqg/TsppoB0vLaAhHQK6KxSsr/bV1fZQoaAZHQHL43q7iADtoB0vbaAhHQK6LGpPykKx1fZQoaAZHQHONvVNHpbFoB0vOaAhHQK6Let9QXRB1fZQoaAZHQHB1V0DEFW5oB0vbaAhHQK6MA1mapgl1fZQoaAZHQHLxCmVJL/VoB0vIaAhHQK6MB0knkT91fZQoaAZHQHCxcH0K7ZpoB0vaaAhHQK6MHGz8gp11fZQoaAZHQHH+SDRMN+doB0u6aAhHQK6MTRyfcvd1fZQoaAZHQGQXm6PKdQRoB03oA2gIR0CujF4txuKodX2UKGgGR0BzY2aF23a0aAdLyGgIR0CujGhSUC7sdX2UKGgGR0BzeD7xd6cBaAdL32gIR0CujK7OeJ53dX2UKGgGR0BwXcX/HYHxaAdL5WgIR0CujLBdD6WPdX2UKGgGR0BymcKtxMnJaAdL52gIR0CujNSyMUAUdX2UKGgGR0Bw4f4pMHryaAdLzmgIR0CujOoRAbADdX2UKGgGR0BybfjcVQANaAdLvmgIR0CujOnkT6BRdX2UKGgGR0By0Y3BHkLhaAdLymgIR0CujTwfp2U0dX2UKGgGR0BxUHiT+vQoaAdLw2gIR0CujWdJz1brdX2UKGgGR0BQkBQemvW6aAdLemgIR0CujdGa6STydX2UKGgGR0BzK/VlPJq7aAdLzWgIR0CujdDghr31dX2UKGgGR0BIv6M72criaAdLfmgIR0Cujj4yGi5/dX2UKGgGR0BxLTUc4o7WaAdLt2gIR0CujlS1maphdX2UKGgGR0BxMSWjXWe6aAdL3GgIR0Cujl6pHZsbdX2UKGgGR0By5wY4yXUpaAdLz2gIR0CujrFmOEM9dX2UKGgGR0Bv0Ck9ECvHaAdLzGgIR0CujrcriEQHdX2UKGgGR0BxgVnanJkoaAdLyGgIR0CujvDkMkQgdX2UKGgGR0ByKbGPxQSBaAdLwmgIR0CujzrOzIFNdX2UKGgGR0Bwr6BJ7LMcaAdLtmgIR0Cuj1WOp84QdX2UKGgGR0BylUQumJm/aAdLv2gIR0Cuj115Sm65dX2UKGgGR0ByL7iIcinpaAdL8WgIR0Cuj3AcLjPwdX2UKGgGR0Bw66VpsXSCaAdL02gIR0CukFM/hVENdX2UKGgGR0BxSAIu5BkaaAdLwGgIR0CukIz37DVIdX2UKGgGR0Bn5rLMcIZ7aAdN6ANoCEdArpCmT5ftyHV9lChoBkdAcl89QGfPHGgHS9JoCEdArpDPJiiItXV9lChoBkdAc7p/yGzrvGgHS9FoCEdArpE05EMLGHV9lChoBkdAb3UDB/I8yWgHS81oCEdArpE9JJ5E+nV9lChoBkdAcjya5PM0QGgHS95oCEdArpGC+Yc/+3V9lChoBkdAcg4N83Mpw2gHS8doCEdArpGBE8aGYnV9lChoBkdAbq8aJhvzfGgHS8xoCEdArpGX0RODa3V9lChoBkdAcx5NRWLgoGgHS8loCEdArpHLKNhmXnVlLg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 1480, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True True True True True True]", "bounded_above": "[ True True True True True True True True]", "_shape": [8], "low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "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": 8, "clip_range": {":type:": "<class 'function'>", ":serialized:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 UTC 2023", "Python": "3.10.6", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
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 sha256:635c8e9fa679d008218d682772469780587175d339aefc55e0f32ebe63e5753a
|
3 |
+
size 146630
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,34 +4,34 @@
|
|
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 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 ",
|
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 |
-
"extract_features": "<function ActorCriticPolicy.extract_features at
|
14 |
-
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at
|
15 |
-
"_predict": "<function ActorCriticPolicy._predict at
|
16 |
-
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at
|
17 |
-
"get_distribution": "<function ActorCriticPolicy.get_distribution at
|
18 |
-
"predict_values": "<function ActorCriticPolicy.predict_values at
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
-
"_abc_impl": "<_abc._abc_data object at
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
24 |
-
"num_timesteps":
|
25 |
-
"_total_timesteps":
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
-
"start_time":
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
-
":serialized:": "
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -41,17 +41,17 @@
|
|
41 |
"_episode_num": 0,
|
42 |
"use_sde": false,
|
43 |
"sde_sample_freq": -1,
|
44 |
-
"_current_progress_remaining": -0.
|
45 |
"_stats_window_size": 100,
|
46 |
"ep_info_buffer": {
|
47 |
":type:": "<class 'collections.deque'>",
|
48 |
-
":serialized:": "
|
49 |
},
|
50 |
"ep_success_buffer": {
|
51 |
":type:": "<class 'collections.deque'>",
|
52 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
},
|
54 |
-
"_n_updates":
|
55 |
"observation_space": {
|
56 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
":serialized:": "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",
|
@@ -84,7 +84,7 @@
|
|
84 |
"vf_coef": 0.5,
|
85 |
"max_grad_norm": 0.5,
|
86 |
"batch_size": 64,
|
87 |
-
"n_epochs":
|
88 |
"clip_range": {
|
89 |
":type:": "<class 'function'>",
|
90 |
":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 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 ",
|
7 |
+
"__init__": "<function ActorCriticPolicy.__init__ at 0x7d9684cbaef0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d9684cbaf80>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d9684cbb010>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d9684cbb0a0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7d9684cbb130>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7d9684cbb1c0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7d9684cbb250>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d9684cbb2e0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7d9684cbb370>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d9684cbb400>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d9684cbb490>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7d9684cbb520>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7d9684cc4bc0>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
24 |
+
"num_timesteps": 2015232,
|
25 |
+
"_total_timesteps": 2000000,
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
+
"start_time": 1690341353196836452,
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
+
":serialized:": "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"
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
41 |
"_episode_num": 0,
|
42 |
"use_sde": false,
|
43 |
"sde_sample_freq": -1,
|
44 |
+
"_current_progress_remaining": -0.007616000000000067,
|
45 |
"_stats_window_size": 100,
|
46 |
"ep_info_buffer": {
|
47 |
":type:": "<class 'collections.deque'>",
|
48 |
+
":serialized:": "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"
|
49 |
},
|
50 |
"ep_success_buffer": {
|
51 |
":type:": "<class 'collections.deque'>",
|
52 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
},
|
54 |
+
"_n_updates": 1480,
|
55 |
"observation_space": {
|
56 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
":serialized:": "gAWVcAIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoECiWCAAAAAAAAAABAQEBAQEBAZRoFEsIhZRoGHSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBAoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaApLCIWUaBh0lFKUjARoaWdolGgQKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgKSwiFlGgYdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=",
|
|
|
84 |
"vf_coef": 0.5,
|
85 |
"max_grad_norm": 0.5,
|
86 |
"batch_size": 64,
|
87 |
+
"n_epochs": 8,
|
88 |
"clip_range": {
|
89 |
":type:": "<class 'function'>",
|
90 |
":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 sha256:0666b686810cd7c77118fb97a077d85f2da549356674a02d96e5d2b9309fb3f6
|
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 43329
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5bc5cc606237c72ec4a7b3097b262024dd3dca94a62fba04ffd5a9eef04aa223
|
3 |
size 43329
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 298.8157152787636, "std_reward": 9.469328827660725, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-26T04:14:11.196772"}
|