Upload PPO LunarLander-v2 trained agent
Browse files- .gitattributes +1 -0
- README.md +36 -0
- config.json +1 -0
- ppo-LunarLander-v2.zip +3 -0
- ppo-LunarLander-v2/_stable_baselines3_version +1 -0
- ppo-LunarLander-v2/data +94 -0
- ppo-LunarLander-v2/policy.optimizer.pth +3 -0
- ppo-LunarLander-v2/policy.pth +3 -0
- ppo-LunarLander-v2/pytorch_variables.pth +3 -0
- ppo-LunarLander-v2/system_info.txt +7 -0
- replay.mp4 +3 -0
- results.json +1 -0
.gitattributes
CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.mp4 filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: stable-baselines3
|
3 |
+
tags:
|
4 |
+
- LunarLander-v2
|
5 |
+
- deep-reinforcement-learning
|
6 |
+
- reinforcement-learning
|
7 |
+
- stable-baselines3
|
8 |
+
model-index:
|
9 |
+
- name: PPO
|
10 |
+
results:
|
11 |
+
- metrics:
|
12 |
+
- type: mean_reward
|
13 |
+
value: 191.06 +/- 84.30
|
14 |
+
name: mean_reward
|
15 |
+
task:
|
16 |
+
type: reinforcement-learning
|
17 |
+
name: reinforcement-learning
|
18 |
+
dataset:
|
19 |
+
name: LunarLander-v2
|
20 |
+
type: LunarLander-v2
|
21 |
+
---
|
22 |
+
|
23 |
+
# **PPO** Agent playing **LunarLander-v2**
|
24 |
+
This is a trained model of a **PPO** agent playing **LunarLander-v2**
|
25 |
+
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
26 |
+
|
27 |
+
## Usage (with Stable-baselines3)
|
28 |
+
TODO: Add your code
|
29 |
+
|
30 |
+
|
31 |
+
```python
|
32 |
+
from stable_baselines3 import ...
|
33 |
+
from huggingface_sb3 import load_from_hub
|
34 |
+
|
35 |
+
...
|
36 |
+
```
|
config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__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 0x7f6abe0d5830>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f6abe0d58c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f6abe0d5950>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f6abe0d59e0>", "_build": "<function ActorCriticPolicy._build at 0x7f6abe0d5a70>", "forward": "<function ActorCriticPolicy.forward at 0x7f6abe0d5b00>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f6abe0d5b90>", "_predict": "<function ActorCriticPolicy._predict at 0x7f6abe0d5c20>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f6abe0d5cb0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f6abe0d5d40>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f6abe0d5dd0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f6abe0b0120>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "gASVwwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLCIWUjANsb3eUjBVudW1weS5jb3JlLm11bHRpYXJyYXmUjAxfcmVjb25zdHJ1Y3SUk5RoBowHbmRhcnJheZSTlEsAhZRDAWKUh5RSlChLAUsIhZRoColDIAAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/lHSUYowEaGlnaJRoEmgUSwCFlGgWh5RSlChLAUsIhZRoColDIAAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/lHSUYowNYm91bmRlZF9iZWxvd5RoEmgUSwCFlGgWh5RSlChLAUsIhZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDCAAAAAAAAAAAlHSUYowNYm91bmRlZF9hYm92ZZRoEmgUSwCFlGgWh5RSlChLAUsIhZRoKolDCAAAAAAAAAAAlHSUYowKX25wX3JhbmRvbZROdWIu", "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:": "gASVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 507904, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1655896689.5475562, "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:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gASVdhAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIUOCdfHqBW0CUhpRSlIwBbJRN6AOMAXSUR0B7hhLQHAymdX2UKGgGaAloD0MIdVWgFoNEYUCUhpRSlGgVTegDaBZHQHuQTmCAc1h1fZQoaAZoCWgPQwgQlUbM7JNfQJSGlFKUaBVN6ANoFkdAe5bojfNzKnV9lChoBmgJaA9DCH9skh/xW19AlIaUUpRoFU3oA2gWR0B8AShakhzOdX2UKGgGaAloD0MIWYY41sX0X0CUhpRSlGgVTegDaBZHQHwDBzBAOax1fZQoaAZoCWgPQwhCQ/8EF0sNwJSGlFKUaBVL9WgWR0B8BOvLX+VDdX2UKGgGaAloD0MI6GnAIGkIYkCUhpRSlGgVTegDaBZHQHwGdgF5fMR1fZQoaAZoCWgPQwgdHOxNDGdgQJSGlFKUaBVN6ANoFkdAfAqLiMo+fXV9lChoBmgJaA9DCJTb9j1qV2JAlIaUUpRoFU3oA2gWR0B8JeYtxuKodX2UKGgGaAloD0MIk1fnGJAtEkCUhpRSlGgVS+doFkdAfDK6qsEJSnV9lChoBmgJaA9DCKbuyi6YmmRAlIaUUpRoFU3oA2gWR0B8O2u+yquKdX2UKGgGaAloD0MIWrvtQnPEYECUhpRSlGgVTegDaBZHQHxFY+jdpIt1fZQoaAZoCWgPQwiitg2jIFhbQJSGlFKUaBVN6ANoFkdAfEcDs+mm+HV9lChoBmgJaA9DCKOVe4FZumBAlIaUUpRoFU3oA2gWR0B8SG0+kgwHdX2UKGgGaAloD0MIi6VIvhKyWECUhpRSlGgVTegDaBZHQHxN7dWQwK11fZQoaAZoCWgPQwh8nj9tVKcIQJSGlFKUaBVLw2gWR0B8dEIC2c8UdX2UKGgGaAloD0MIfZOmQdGwOkCUhpRSlGgVTQABaBZHQHx37UXpGF11fZQoaAZoCWgPQwgF4J9SJYpfQJSGlFKUaBVN6ANoFkdAfIiT72tdRnV9lChoBmgJaA9DCH7hlSTP7lhAlIaUUpRoFU3oA2gWR0B8jKjUNKAbdX2UKGgGaAloD0MIlIjwL4KiMMCUhpRSlGgVS9VoFkdAfKy5LRKHwnV9lChoBmgJaA9DCI//AkGA3lJAlIaUUpRoFU3oA2gWR0B8sWk690zTdX2UKGgGaAloD0MIJSL8i6D+YUCUhpRSlGgVTegDaBZHQHzBLVawD/51fZQoaAZoCWgPQwgZraOqCShRQJSGlFKUaBVN6ANoFkdAfMimSyMUAXV9lChoBmgJaA9DCNOiPsmdMmFAlIaUUpRoFU3oA2gWR0B9NHohY/3WdX2UKGgGaAloD0MIOQ68Wu4aX0CUhpRSlGgVTegDaBZHQH04oUrTYul1fZQoaAZoCWgPQwj1nPS+8VNMQJSGlFKUaBVN6ANoFkdAfTpc32mHg3V9lChoBmgJaA9DCGMJa2PsIE1AlIaUUpRoFU3oA2gWR0B9Px5rxiG4dX2UKGgGaAloD0MIE5uPa0NJT0CUhpRSlGgVTegDaBZHQH1gCGetjkN1fZQoaAZoCWgPQwjkvWplwuNGQJSGlFKUaBVLpWgWR0B9YEskIHC5dX2UKGgGaAloD0MIoyO5/IcpWECUhpRSlGgVTegDaBZHQH1ueajN6gN1fZQoaAZoCWgPQwhxBKkUOzY3QJSGlFKUaBVN6ANoFkdAfYHnGbTc7HV9lChoBmgJaA9DCHGuYYbGbGBAlIaUUpRoFU3oA2gWR0B9hTlbNbC8dX2UKGgGaAloD0MI/Uy9bpGFYECUhpRSlGgVTegDaBZHQH2LXUYsNDt1fZQoaAZoCWgPQwjjpDDvcTYkwJSGlFKUaBVL5GgWR0B9o1NVR1oydX2UKGgGaAloD0MIn+OjxRlAY0CUhpRSlGgVTegDaBZHQH2znbdrO7h1fZQoaAZoCWgPQwhYN94dGbsZQJSGlFKUaBVLx2gWR0B9uxw6ySmqdX2UKGgGaAloD0MIvayJBb7DUkCUhpRSlGgVTegDaBZHQH3Be2d/axp1fZQoaAZoCWgPQwjNd/ATh1thQJSGlFKUaBVN6ANoFkdAfcWW2gFotnV9lChoBmgJaA9DCP63kh0blFxAlIaUUpRoFU3oA2gWR0B95nxhDw6RdX2UKGgGaAloD0MI9RH4w8+oXkCUhpRSlGgVTegDaBZHQH3rI3rD6311fZQoaAZoCWgPQwhBZ9Km6jYhQJSGlFKUaBVLtmgWR0B97yU/wAlwdX2UKGgGaAloD0MILEgzFk1sWUCUhpRSlGgVTegDaBZHQH36fHPu5SZ1fZQoaAZoCWgPQwgkfO9v0IJjQJSGlFKUaBVN6ANoFkdAfgGSamXPaHV9lChoBmgJaA9DCMSxLm6j9GNAlIaUUpRoFU3oA2gWR0B+bMTL4etCdX2UKGgGaAloD0MImRJJ9LI8YECUhpRSlGgVTegDaBZHQH5yt4Z/CqJ1fZQoaAZoCWgPQwgzb9V1qCxEQJSGlFKUaBVN6ANoFkdAfnfMqjJuEXV9lChoBmgJaA9DCBHhXwSNJ13AlIaUUpRoFU2RAWgWR0B+jR/I8yN5dX2UKGgGaAloD0MIeHsQAvLSWECUhpRSlGgVTegDaBZHQH6XvP9kz411fZQoaAZoCWgPQwiJIw9EFnJTQJSGlFKUaBVN6ANoFkdAfpf+OwPiDXV9lChoBmgJaA9DCJjD7juGC1lAlIaUUpRoFU3oA2gWR0B+uRG9YfW+dX2UKGgGaAloD0MIrTWU2ovQRECUhpRSlGgVTegDaBZHQH68lQ2uPmx1fZQoaAZoCWgPQwjn4JnQJG5dQJSGlFKUaBVN6ANoFkdAft41MdtEX3V9lChoBmgJaA9DCLlt36P+QirAlIaUUpRoFUvTaBZHQH7uXndO6/Z1fZQoaAZoCWgPQwiVD0HV6ABeQJSGlFKUaBVN6ANoFkdAfu6of0VafXV9lChoBmgJaA9DCB8xem4h+mNAlIaUUpRoFU3oA2gWR0B+9ec9W6sidX2UKGgGaAloD0MIe00PCsreYkCUhpRSlGgVTegDaBZHQH7/yBf8dgh1fZQoaAZoCWgPQwjtD5Tb9qdgQJSGlFKUaBVN6ANoFkdAfyXyTINmUXV9lChoBmgJaA9DCKYqbXGNbGJAlIaUUpRoFU3oA2gWR0B/KjyYoiLVdX2UKGgGaAloD0MIEeFfBI1aXkCUhpRSlGgVTegDaBZHQH82ZRwZOzp1fZQoaAZoCWgPQwhRvqCFBAhaQJSGlFKUaBVN6ANoFkdAfz3VNpM6BHV9lChoBmgJaA9DCIYEjC5vDlpAlIaUUpRoFU3oA2gWR0B/ZbWlMyrQdX2UKGgGaAloD0MIYthhTPrvV0CUhpRSlGgVTegDaBZHQH+yna37UG51fZQoaAZoCWgPQwjO4VrtYaVWQJSGlFKUaBVN6ANoFkdAf7gDye7L+3V9lChoBmgJaA9DCHEfuTVprmRAlIaUUpRoFU3oA2gWR0B/znyc0+C9dX2UKGgGaAloD0MIkkCDTZ2jNUCUhpRSlGgVTegDaBZHQH/Y6vFFUhp1fZQoaAZoCWgPQwjr4GBvYt1dQJSGlFKUaBVN6ANoFkdAf9krvLHMlnV9lChoBmgJaA9DCDNPrimQdTVAlIaUUpRoFUuxaBZHQH/3G4ZuQ6p1fZQoaAZoCWgPQwgyVwbVBm1hQJSGlFKUaBVN6ANoFkdAf/wfChvitXV9lChoBmgJaA9DCGUdjq7SQWNAlIaUUpRoFU3oA2gWR0CADiQgcLjQdX2UKGgGaAloD0MI1h9hGDBwZkCUhpRSlGgVTVcBaBZHQIAVVtl7MPl1fZQoaAZoCWgPQwho6Qq2kX5iQJSGlFKUaBVN6ANoFkdAgBZ13EAHV3V9lChoBmgJaA9DCGGnWDWIQWFAlIaUUpRoFU3oA2gWR0CAFpv3rUsndX2UKGgGaAloD0MIH75MFCFyY0CUhpRSlGgVTegDaBZHQIAZ1JQLux91fZQoaAZoCWgPQwg0LhwIydJfQJSGlFKUaBVN6ANoFkdAgB5GKyfL93V9lChoBmgJaA9DCPxTqkTZDVtAlIaUUpRoFU3oA2gWR0CALrzOHFgldX2UKGgGaAloD0MIhjsXRnpuYECUhpRSlGgVTegDaBZHQIAwjZYgaFV1fZQoaAZoCWgPQwgIV0Chnu9gQJSGlFKUaBVN6ANoFkdAgDWyA6Mir3V9lChoBmgJaA9DCAZjRKLQDlxAlIaUUpRoFU3oA2gWR0CAORzGPxQSdX2UKGgGaAloD0MImWN5Vz0QTkCUhpRSlGgVTegDaBZHQIBLwfuCwr11fZQoaAZoCWgPQwj1LAjl/UJjQJSGlFKUaBVN6ANoFkdAgE7JW/8EV3V9lChoBmgJaA9DCMdmR6pvlmJAlIaUUpRoFU3oA2gWR0CAdMyQgcLjdX2UKGgGaAloD0MI5nXEIRvIO8CUhpRSlGgVTQIBaBZHQIB8UZ1mrbR1fZQoaAZoCWgPQwh9rrZif3dXQJSGlFKUaBVN6ANoFkdAgIYu9WZJCnV9lChoBmgJaA9DCLGjcajfIWZAlIaUUpRoFU2QA2gWR0CAjANaQmu1dX2UKGgGaAloD0MIn5EIjWD2XECUhpRSlGgVTegDaBZHQICaUQf6oEV1fZQoaAZoCWgPQwiS66aUV7NiQJSGlFKUaBVN6ANoFkdAgKxWZqmCRXV9lChoBmgJaA9DCEwW9x+ZwlFAlIaUUpRoFU3oA2gWR0CAs8OT7l7udX2UKGgGaAloD0MIeEZblUQ0VkCUhpRSlGgVTegDaBZHQIC06SHM2WJ1fZQoaAZoCWgPQwhZUYNpGO1XQJSGlFKUaBVN6ANoFkdAgLUQ9RrJsHV9lChoBmgJaA9DCNHno4y4yFhAlIaUUpRoFU3oA2gWR0CAuJpbD/EPdX2UKGgGaAloD0MIpU+r6A+8XECUhpRSlGgVTegDaBZHQIC88Rvm5lR1fZQoaAZoCWgPQwh/bJIf8ZlAQJSGlFKUaBVNDgFoFkdAgMs3TNMXanV9lChoBmgJaA9DCCUDQBW31mFAlIaUUpRoFU3oA2gWR0CAzSp2ECeVdX2UKGgGaAloD0MId700RYBSXkCUhpRSlGgVTegDaBZHQIDO9SZSeiB1fZQoaAZoCWgPQwiWXTC45q5WQJSGlFKUaBVN6ANoFkdAgNPgYgq3E3V9lChoBmgJaA9DCF3+Q/rtR2tAlIaUUpRoFU3+AWgWR0CA1xC+De0pdX2UKGgGaAloD0MIbMuAs5T+SkCUhpRSlGgVS9toFkdAgOiCtihFmXV9lChoBmgJaA9DCAiPNo5Y+mRAlIaUUpRoFU3oA2gWR0CA6f0TURWcdX2UKGgGaAloD0MIHTuoxHUaW0CUhpRSlGgVTegDaBZHQIDs1S619fF1fZQoaAZoCWgPQwj1EmOZ/h9hQJSGlFKUaBVN6ANoFkdAgO98AJb+tXVlLg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 124, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022", "Python": "3.7.13", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
|
ppo-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83c4cc300222814d556f408ff82dee3d8051940ff45ea9a5481cf5f73c37c358
|
3 |
+
size 144144
|
ppo-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.5.0
|
ppo-LunarLander-v2/data
ADDED
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"policy_class": {
|
3 |
+
":type:": "<class 'abc.ABCMeta'>",
|
4 |
+
":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
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 0x7f6abe0d5830>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f6abe0d58c0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f6abe0d5950>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f6abe0d59e0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f6abe0d5a70>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f6abe0d5b00>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f6abe0d5b90>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f6abe0d5c20>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f6abe0d5cb0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f6abe0d5d40>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f6abe0d5dd0>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f6abe0b0120>"
|
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
|
29 |
+
],
|
30 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
31 |
+
"high": "[inf inf inf inf inf inf inf inf]",
|
32 |
+
"bounded_below": "[False False False False False False False False]",
|
33 |
+
"bounded_above": "[False False False False False False False False]",
|
34 |
+
"_np_random": null
|
35 |
+
},
|
36 |
+
"action_space": {
|
37 |
+
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
38 |
+
":serialized:": "gASVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
39 |
+
"n": 4,
|
40 |
+
"_shape": [],
|
41 |
+
"dtype": "int64",
|
42 |
+
"_np_random": null
|
43 |
+
},
|
44 |
+
"n_envs": 16,
|
45 |
+
"num_timesteps": 507904,
|
46 |
+
"_total_timesteps": 500000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1655896689.5475562,
|
51 |
+
"learning_rate": 0.0003,
|
52 |
+
"tensorboard_log": null,
|
53 |
+
"lr_schedule": {
|
54 |
+
":type:": "<class 'function'>",
|
55 |
+
":serialized:": "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"
|
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'>",
|
63 |
+
":serialized:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="
|
64 |
+
},
|
65 |
+
"_last_original_obs": null,
|
66 |
+
"_episode_num": 0,
|
67 |
+
"use_sde": false,
|
68 |
+
"sde_sample_freq": -1,
|
69 |
+
"_current_progress_remaining": -0.015808000000000044,
|
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:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
+
},
|
78 |
+
"_n_updates": 124,
|
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,
|
85 |
+
"batch_size": 64,
|
86 |
+
"n_epochs": 4,
|
87 |
+
"clip_range": {
|
88 |
+
":type:": "<class 'function'>",
|
89 |
+
":serialized:": "gASVvwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxIL3Vzci9sb2NhbC9saWIvcHl0aG9uMy43L2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
|
90 |
+
},
|
91 |
+
"clip_range_vf": null,
|
92 |
+
"normalize_advantage": true,
|
93 |
+
"target_kl": null
|
94 |
+
}
|
ppo-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5abc0035a72d386e423b658080f5ed23e6f5c7d4b8ef1e3bc5c9a665e032f52d
|
3 |
+
size 84829
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4bde5f6ed7e3413fcdf2ca7767bcf6863f4e3d5ca0ef50a9ab75c1a9567643e3
|
3 |
+
size 43201
|
ppo-LunarLander-v2/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
|
3 |
+
size 431
|
ppo-LunarLander-v2/system_info.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
OS: Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022
|
2 |
+
Python: 3.7.13
|
3 |
+
Stable-Baselines3: 1.5.0
|
4 |
+
PyTorch: 1.11.0+cu113
|
5 |
+
GPU Enabled: True
|
6 |
+
Numpy: 1.21.6
|
7 |
+
Gym: 0.21.0
|
replay.mp4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4011d030f5561b74cb37e72efe4c02f3dc481343fa4ac6a50084b5f9e26d3ff3
|
3 |
+
size 184781
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 191.06361991420542, "std_reward": 84.29773979489588, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-22T11:28:35.695978"}
|