charleschen2022
commited on
Commit
•
4073245
1
Parent(s):
889a316
first submit of lunarlander
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 +96 -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: 247.27 +/- 17.57
|
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 0x7ff3a7f40ee0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff3a7f40f70>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff3a7f42040>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff3a7f420d0>", "_build": "<function ActorCriticPolicy._build at 0x7ff3a7f42160>", "forward": "<function ActorCriticPolicy.forward at 0x7ff3a7f421f0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ff3a7f42280>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff3a7f42310>", "_predict": "<function ActorCriticPolicy._predict at 0x7ff3a7f423a0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff3a7f42430>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff3a7f424c0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff3a7f42550>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7ff3a7f45580>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1681936534798432811, "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, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 252, "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, "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-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.9.16", "Stable-Baselines3": "1.8.0", "PyTorch": "2.0.0+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Gym": "0.21.0"}}
|
ppo_LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e93101d204dd1af766f697836dafffb6ebd7c46bfcad5e681ca21e2180244b2
|
3 |
+
size 147383
|
ppo_LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.8.0
|
ppo_LunarLander-v2/data
ADDED
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 0x7ff3a7f40ee0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff3a7f40f70>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff3a7f42040>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff3a7f420d0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7ff3a7f42160>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7ff3a7f421f0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7ff3a7f42280>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff3a7f42310>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7ff3a7f423a0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff3a7f42430>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff3a7f424c0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff3a7f42550>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7ff3a7f45580>"
|
21 |
+
},
|
22 |
+
"verbose": 1,
|
23 |
+
"policy_kwargs": {},
|
24 |
+
"num_timesteps": 1015808,
|
25 |
+
"_total_timesteps": 1000000,
|
26 |
+
"_num_timesteps_at_start": 0,
|
27 |
+
"seed": null,
|
28 |
+
"action_noise": null,
|
29 |
+
"start_time": 1681936534798432811,
|
30 |
+
"learning_rate": 0.0003,
|
31 |
+
"tensorboard_log": null,
|
32 |
+
"lr_schedule": {
|
33 |
+
":type:": "<class 'function'>",
|
34 |
+
":serialized:": "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"
|
35 |
+
},
|
36 |
+
"_last_obs": {
|
37 |
+
":type:": "<class 'numpy.ndarray'>",
|
38 |
+
":serialized:": "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"
|
39 |
+
},
|
40 |
+
"_last_episode_starts": {
|
41 |
+
":type:": "<class 'numpy.ndarray'>",
|
42 |
+
":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
43 |
+
},
|
44 |
+
"_last_original_obs": null,
|
45 |
+
"_episode_num": 0,
|
46 |
+
"use_sde": false,
|
47 |
+
"sde_sample_freq": -1,
|
48 |
+
"_current_progress_remaining": -0.015808000000000044,
|
49 |
+
"_stats_window_size": 100,
|
50 |
+
"ep_info_buffer": {
|
51 |
+
":type:": "<class 'collections.deque'>",
|
52 |
+
":serialized:": "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"
|
53 |
+
},
|
54 |
+
"ep_success_buffer": {
|
55 |
+
":type:": "<class 'collections.deque'>",
|
56 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
57 |
+
},
|
58 |
+
"_n_updates": 252,
|
59 |
+
"observation_space": {
|
60 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
61 |
+
":serialized:": "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",
|
62 |
+
"dtype": "float32",
|
63 |
+
"_shape": [
|
64 |
+
8
|
65 |
+
],
|
66 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
67 |
+
"high": "[inf inf inf inf inf inf inf inf]",
|
68 |
+
"bounded_below": "[False False False False False False False False]",
|
69 |
+
"bounded_above": "[False False False False False False False False]",
|
70 |
+
"_np_random": null
|
71 |
+
},
|
72 |
+
"action_space": {
|
73 |
+
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
74 |
+
":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
75 |
+
"n": 4,
|
76 |
+
"_shape": [],
|
77 |
+
"dtype": "int64",
|
78 |
+
"_np_random": null
|
79 |
+
},
|
80 |
+
"n_envs": 16,
|
81 |
+
"n_steps": 1024,
|
82 |
+
"gamma": 0.999,
|
83 |
+
"gae_lambda": 0.98,
|
84 |
+
"ent_coef": 0.01,
|
85 |
+
"vf_coef": 0.5,
|
86 |
+
"max_grad_norm": 0.5,
|
87 |
+
"batch_size": 64,
|
88 |
+
"n_epochs": 4,
|
89 |
+
"clip_range": {
|
90 |
+
":type:": "<class 'function'>",
|
91 |
+
":serialized:": "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"
|
92 |
+
},
|
93 |
+
"clip_range_vf": null,
|
94 |
+
"normalize_advantage": true,
|
95 |
+
"target_kl": null
|
96 |
+
}
|
ppo_LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:95887cbe37af0c9c0b0e80f0b565acac46843d841fb285009dca9c540206e508
|
3 |
+
size 87929
|
ppo_LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c9ba5f56dcd723709ef190753dafa8089330d22891b0056fde0e1788b9c03ea
|
3 |
+
size 43329
|
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-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
|
2 |
+
- Python: 3.9.16
|
3 |
+
- Stable-Baselines3: 1.8.0
|
4 |
+
- PyTorch: 2.0.0+cu118
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.22.4
|
7 |
+
- Gym: 0.21.0
|
replay.mp4
ADDED
Binary file (261 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 247.27148675426528, "std_reward": 17.572093542673745, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-04-19T21:07:58.711523"}
|