Upload PPO Lunarlander testing 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: 209.50 +/- 25.82
|
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 0x7f9b19015160>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f9b190151f0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f9b19015280>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f9b19015310>", "_build": "<function ActorCriticPolicy._build at 0x7f9b190153a0>", "forward": "<function ActorCriticPolicy.forward at 0x7f9b19015430>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f9b190154c0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f9b19015550>", "_predict": "<function ActorCriticPolicy._predict at 0x7f9b190155e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f9b19015670>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f9b19015700>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f9b19015790>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f9b19010510>"}, "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": 507904, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1680840695642366653, "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": 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-5.4.0-97-generic-x86_64-with-glibc2.10 # 110-Ubuntu SMP Thu Jan 13 18:22:13 UTC 2022", "Python": "3.8.15", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1", "GPU Enabled": "True", "Numpy": "1.23.5", "Gym": "0.21.0"}}
|
ppo-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f183c7e09e3fefd335d1090656fb44c66ea62fd37da74b125395e887654822f
|
3 |
+
size 147712
|
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 0x7f9b19015160>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f9b190151f0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f9b19015280>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f9b19015310>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f9b190153a0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f9b19015430>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f9b190154c0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f9b19015550>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f9b190155e0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f9b19015670>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f9b19015700>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f9b19015790>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc_data object at 0x7f9b19010510>"
|
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": 507904,
|
47 |
+
"_total_timesteps": 500000,
|
48 |
+
"_num_timesteps_at_start": 0,
|
49 |
+
"seed": null,
|
50 |
+
"action_noise": null,
|
51 |
+
"start_time": 1680840695642366653,
|
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": 124,
|
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 sha256:684efd829bb473b2de69f7266d039fd1dbb7fb968192cfade4efc9fe9f8c0ca9
|
3 |
+
size 88057
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e504665b9a9fbd7f8a580e535eab4bd0cbc2b6124ec0241fe228a16bf0d05d1c
|
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-5.4.0-97-generic-x86_64-with-glibc2.10 # 110-Ubuntu SMP Thu Jan 13 18:22:13 UTC 2022
|
2 |
+
- Python: 3.8.15
|
3 |
+
- Stable-Baselines3: 1.7.0
|
4 |
+
- PyTorch: 1.13.1
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.23.5
|
7 |
+
- Gym: 0.21.0
|
replay.mp4
ADDED
Binary file (260 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 209.49682650855092, "std_reward": 25.823449770023924, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-04-06T22:31:27.510728"}
|