first version
Browse files- README.md +37 -0
- config.json +1 -0
- ppo-LunarLander-ver2.zip +3 -0
- ppo-LunarLander-ver2/_stable_baselines3_version +1 -0
- ppo-LunarLander-ver2/data +95 -0
- ppo-LunarLander-ver2/policy.optimizer.pth +3 -0
- ppo-LunarLander-ver2/policy.pth +3 -0
- ppo-LunarLander-ver2/pytorch_variables.pth +3 -0
- ppo-LunarLander-ver2/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: 265.28 +/- 17.66
|
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 0x7f8c9b444820>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f8c9b4448b0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f8c9b444940>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f8c9b4449d0>", "_build": "<function ActorCriticPolicy._build at 0x7f8c9b444a60>", "forward": "<function ActorCriticPolicy.forward at 0x7f8c9b444af0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f8c9b444b80>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f8c9b444c10>", "_predict": "<function ActorCriticPolicy._predict at 0x7f8c9b444ca0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f8c9b444d30>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f8c9b444dc0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f8c9b444e50>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f8c9b440720>"}, "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": 1676550488010534575, "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": 310, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "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-ver2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5ebc220b536eb8d43f41f35a5787da17aebcad420be689f57dd79f3121caa86
|
3 |
+
size 146801
|
ppo-LunarLander-ver2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.7.0
|
ppo-LunarLander-ver2/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 0x7f8c9b444820>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f8c9b4448b0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f8c9b444940>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f8c9b4449d0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f8c9b444a60>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f8c9b444af0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f8c9b444b80>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f8c9b444c10>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f8c9b444ca0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f8c9b444d30>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f8c9b444dc0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f8c9b444e50>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc_data object at 0x7f8c9b440720>"
|
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": 1676550488010534575,
|
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": 310,
|
80 |
+
"n_steps": 2048,
|
81 |
+
"gamma": 0.99,
|
82 |
+
"gae_lambda": 0.95,
|
83 |
+
"ent_coef": 0.01,
|
84 |
+
"vf_coef": 0.5,
|
85 |
+
"max_grad_norm": 0.5,
|
86 |
+
"batch_size": 64,
|
87 |
+
"n_epochs": 10,
|
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-ver2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b939cd4b3df6d988ba1c66f47c87fda4c59028410a6d83f2fb11197255aa306
|
3 |
+
size 87545
|
ppo-LunarLander-ver2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09981d8e33d1f78a0540b3950567d7e1ba0b81d06e2afe70c4478c9cdfca2ed0
|
3 |
+
size 43265
|
ppo-LunarLander-ver2/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-ver2/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 (204 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 265.27682099495166, "std_reward": 17.658316155889256, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-16T12:58:59.637043"}
|