Test commit
Browse files- README.md +35 -1
- 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
CHANGED
@@ -1,3 +1,37 @@
|
|
1 |
---
|
2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: 251.40 +/- 16.88
|
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 0x7f6bee898ee0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f6bee898f70>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f6bee89d040>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f6bee89d0d0>", "_build": "<function ActorCriticPolicy._build at 0x7f6bee89d160>", "forward": "<function ActorCriticPolicy.forward at 0x7f6bee89d1f0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f6bee89d280>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f6bee89d310>", "_predict": "<function ActorCriticPolicy._predict at 0x7f6bee89d3a0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f6bee89d430>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f6bee89d4c0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f6bee89d550>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f6bee89a120>"}, "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": 1674223681662890539, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAFpVQr7oOfY9BrH2PaYuLL7+E5m8wGvSPAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": "False", "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:dacbb2b929390538d54d28c5bbd96924f39c50fe98579c117a5dae15086df5e4
|
3 |
+
size 146247
|
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 0x7f6bee898ee0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f6bee898f70>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f6bee89d040>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f6bee89d0d0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f6bee89d160>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f6bee89d1f0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f6bee89d280>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f6bee89d310>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f6bee89d3a0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f6bee89d430>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f6bee89d4c0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f6bee89d550>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc_data object at 0x7f6bee89a120>"
|
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": 1674223681662890539,
|
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:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAFpVQr7oOfY9BrH2PaYuLL7+E5m8wGvSPAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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 |
+
}
|
ppo-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0465cc04a0eb85c19c5d90c2d219bb2267fcb7b952f984e9f0dd478916daf237
|
3 |
+
size 87545
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9c5b71d1bf2d66d0cfbe84febe2767eab03c832e49e1c5014c18efaf614d9ab
|
3 |
+
size 43265
|
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: False
|
6 |
+
- Numpy: 1.21.6
|
7 |
+
- Gym: 0.21.0
|
replay.mp4
ADDED
Binary file (221 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 251.39781499999998, "std_reward": 16.882140089396206, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-20T14:36:34.247158"}
|