arodriguez
commited on
Commit
•
3e0c189
1
Parent(s):
34d8c42
Upload PPO LunarLander-v2 trained agent
Browse files- README.md +37 -0
- config.json +1 -0
- ppo-LunarLander-v2.zip +3 -0
- ppo-LunarLander-v2/_stable_baselines3_version +1 -0
- ppo-LunarLander-v2/data +95 -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 +0 -0
- results.json +1 -0
README.md
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
- task:
|
12 |
+
type: reinforcement-learning
|
13 |
+
name: reinforcement-learning
|
14 |
+
dataset:
|
15 |
+
name: LunarLander-v2
|
16 |
+
type: LunarLander-v2
|
17 |
+
metrics:
|
18 |
+
- type: mean_reward
|
19 |
+
value: 272.54 +/- 19.45
|
20 |
+
name: mean_reward
|
21 |
+
verified: false
|
22 |
+
---
|
23 |
+
|
24 |
+
# **PPO** Agent playing **LunarLander-v2**
|
25 |
+
This is a trained model of a **PPO** agent playing **LunarLander-v2**
|
26 |
+
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
27 |
+
|
28 |
+
## Usage (with Stable-baselines3)
|
29 |
+
TODO: Add your code
|
30 |
+
|
31 |
+
|
32 |
+
```python
|
33 |
+
from stable_baselines3 import ...
|
34 |
+
from huggingface_sb3 import load_from_hub
|
35 |
+
|
36 |
+
...
|
37 |
+
```
|
config.json
ADDED
@@ -0,0 +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 0x7fba85ab7d30>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fba85ab7dc0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fba85ab7e50>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fba85ab7ee0>", "_build": "<function ActorCriticPolicy._build at 0x7fba85ab7f70>", "forward": "<function ActorCriticPolicy.forward at 0x7fba85abc040>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fba85abc0d0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fba85abc160>", "_predict": "<function ActorCriticPolicy._predict at 0x7fba85abc1f0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fba85abc280>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fba85abc310>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fba85abc3a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fba85aa7c60>"}, "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": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1674740471945515127, "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": -0.015808000000000044, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 248, "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-5.10.147+-x86_64-with-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.8.10", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu116", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
|
ppo-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33295d69e53cf19eef6ed58f5b1815f8218d0c9cf5097b06b255339572fe5b1d
|
3 |
+
size 147340
|
ppo-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.7.0
|
ppo-LunarLander-v2/data
ADDED
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"policy_class": {
|
3 |
+
":type:": "<class 'abc.ABCMeta'>",
|
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 0x7fba85ab7d30>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fba85ab7dc0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fba85ab7e50>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fba85ab7ee0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fba85ab7f70>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fba85abc040>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7fba85abc0d0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fba85abc160>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fba85abc1f0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fba85abc280>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fba85abc310>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fba85abc3a0>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc_data object at 0x7fba85aa7c60>"
|
21 |
+
},
|
22 |
+
"verbose": 1,
|
23 |
+
"policy_kwargs": {},
|
24 |
+
"observation_space": {
|
25 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
26 |
+
":serialized:": "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",
|
27 |
+
"dtype": "float32",
|
28 |
+
"_shape": [
|
29 |
+
8
|
30 |
+
],
|
31 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
32 |
+
"high": "[inf inf inf inf inf inf inf inf]",
|
33 |
+
"bounded_below": "[False False False False False False False False]",
|
34 |
+
"bounded_above": "[False False False False False False False False]",
|
35 |
+
"_np_random": null
|
36 |
+
},
|
37 |
+
"action_space": {
|
38 |
+
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
39 |
+
":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
40 |
+
"n": 4,
|
41 |
+
"_shape": [],
|
42 |
+
"dtype": "int64",
|
43 |
+
"_np_random": null
|
44 |
+
},
|
45 |
+
"n_envs": 16,
|
46 |
+
"num_timesteps": 1015808,
|
47 |
+
"_total_timesteps": 1000000,
|
48 |
+
"_num_timesteps_at_start": 0,
|
49 |
+
"seed": null,
|
50 |
+
"action_noise": null,
|
51 |
+
"start_time": 1674740471945515127,
|
52 |
+
"learning_rate": 0.0003,
|
53 |
+
"tensorboard_log": null,
|
54 |
+
"lr_schedule": {
|
55 |
+
":type:": "<class 'function'>",
|
56 |
+
":serialized:": "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"
|
57 |
+
},
|
58 |
+
"_last_obs": {
|
59 |
+
":type:": "<class 'numpy.ndarray'>",
|
60 |
+
":serialized:": "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"
|
61 |
+
},
|
62 |
+
"_last_episode_starts": {
|
63 |
+
":type:": "<class 'numpy.ndarray'>",
|
64 |
+
":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
65 |
+
},
|
66 |
+
"_last_original_obs": null,
|
67 |
+
"_episode_num": 0,
|
68 |
+
"use_sde": false,
|
69 |
+
"sde_sample_freq": -1,
|
70 |
+
"_current_progress_remaining": -0.015808000000000044,
|
71 |
+
"ep_info_buffer": {
|
72 |
+
":type:": "<class 'collections.deque'>",
|
73 |
+
":serialized:": "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"
|
74 |
+
},
|
75 |
+
"ep_success_buffer": {
|
76 |
+
":type:": "<class 'collections.deque'>",
|
77 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
78 |
+
},
|
79 |
+
"_n_updates": 248,
|
80 |
+
"n_steps": 1024,
|
81 |
+
"gamma": 0.999,
|
82 |
+
"gae_lambda": 0.98,
|
83 |
+
"ent_coef": 0.01,
|
84 |
+
"vf_coef": 0.5,
|
85 |
+
"max_grad_norm": 0.5,
|
86 |
+
"batch_size": 64,
|
87 |
+
"n_epochs": 4,
|
88 |
+
"clip_range": {
|
89 |
+
":type:": "<class 'function'>",
|
90 |
+
":serialized:": "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"
|
91 |
+
},
|
92 |
+
"clip_range_vf": null,
|
93 |
+
"normalize_advantage": true,
|
94 |
+
"target_kl": null
|
95 |
+
}
|
ppo-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:058e579837245bb691133af9e965f2f83d66d0d7ac7bce1e2c7eba55a8356140
|
3 |
+
size 87929
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d5fe62cde8898c6d2857cb6af27fb6fc36c5bac1cba592b87c3d8fdd9d7a6ba
|
3 |
+
size 43393
|
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-5.10.147+-x86_64-with-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
|
2 |
+
- Python: 3.8.10
|
3 |
+
- Stable-Baselines3: 1.7.0
|
4 |
+
- PyTorch: 1.13.1+cu116
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.21.6
|
7 |
+
- Gym: 0.21.0
|
replay.mp4
ADDED
Binary file (235 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 272.536008714437, "std_reward": 19.44519020011684, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-26T13:59:35.205202"}
|