lyusungwon
commited on
Commit
•
f73126b
1
Parent(s):
ca0d77b
Upload PPO LunarLander-v2 trained agent
Browse files- README.md +37 -0
- config.json +1 -0
- replay.mp4 +0 -0
- results.json +1 -0
- sungwon-ppo-LunarLander-v2.zip +3 -0
- sungwon-ppo-LunarLander-v2/_stable_baselines3_version +1 -0
- sungwon-ppo-LunarLander-v2/data +95 -0
- sungwon-ppo-LunarLander-v2/policy.optimizer.pth +3 -0
- sungwon-ppo-LunarLander-v2/policy.pth +3 -0
- sungwon-ppo-LunarLander-v2/pytorch_variables.pth +3 -0
- sungwon-ppo-LunarLander-v2/system_info.txt +7 -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: 231.41 +/- 21.39
|
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 0x7f38f2364940>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f38f23649d0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f38f2364a60>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f38f2364af0>", "_build": "<function ActorCriticPolicy._build at 0x7f38f2364b80>", "forward": "<function ActorCriticPolicy.forward at 0x7f38f2364c10>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f38f2364ca0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f38f2364d30>", "_predict": "<function ActorCriticPolicy._predict at 0x7f38f2364dc0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f38f2364e50>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f38f2364ee0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f38f2364f70>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f38f2359e10>"}, "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": 1, "num_timesteps": 1000448, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1674005279623493985, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAADH+L3S368/osDbvk/8Ob7QHA++QmyYvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.00044800000000000395, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 3908, "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"}}
|
replay.mp4
ADDED
Binary file (242 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 231.41480455455948, "std_reward": 21.386488295953328, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-18T02:07:04.876269"}
|
sungwon-ppo-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51840791990a019255b36a2fb7542f47d3f47ec4c17c84072bef2bd5f6ecfec8
|
3 |
+
size 146766
|
sungwon-ppo-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.7.0
|
sungwon-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 0x7f38f2364940>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f38f23649d0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f38f2364a60>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f38f2364af0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f38f2364b80>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f38f2364c10>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f38f2364ca0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f38f2364d30>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f38f2364dc0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f38f2364e50>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f38f2364ee0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f38f2364f70>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc_data object at 0x7f38f2359e10>"
|
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": 1,
|
46 |
+
"num_timesteps": 1000448,
|
47 |
+
"_total_timesteps": 1000000,
|
48 |
+
"_num_timesteps_at_start": 0,
|
49 |
+
"seed": null,
|
50 |
+
"action_noise": null,
|
51 |
+
"start_time": 1674005279623493985,
|
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:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAADH+L3S368/osDbvk/8Ob7QHA++QmyYvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
|
61 |
+
},
|
62 |
+
"_last_episode_starts": {
|
63 |
+
":type:": "<class 'numpy.ndarray'>",
|
64 |
+
":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
|
65 |
+
},
|
66 |
+
"_last_original_obs": null,
|
67 |
+
"_episode_num": 0,
|
68 |
+
"use_sde": false,
|
69 |
+
"sde_sample_freq": -1,
|
70 |
+
"_current_progress_remaining": -0.00044800000000000395,
|
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": 3908,
|
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 |
+
}
|
sungwon-ppo-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f8565ac088a6b84555c14a440e30fc1109dcd7574333cee7d28e8f6a10a017e
|
3 |
+
size 87929
|
sungwon-ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0c85be7b68a1418d16d96724232d549003ff5d9e3c117d1360205a3d2e802fc
|
3 |
+
size 43393
|
sungwon-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
|
sungwon-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
|