juanmi1234
commited on
Commit
•
6f1878a
1
Parent(s):
c79c951
Upload PPO LunarLander-v2 trained 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 +94 -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: 240.41 +/- 23.32
|
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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 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 0x7f535b1535e0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f535b153670>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f535b153700>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f535b153790>", "_build": "<function ActorCriticPolicy._build at 0x7f535b153820>", "forward": "<function ActorCriticPolicy.forward at 0x7f535b1538b0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f535b153940>", "_predict": "<function ActorCriticPolicy._predict at 0x7f535b1539d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f535b153a60>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f535b153af0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f535b153b80>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f535b149e70>"}, "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": 1670532185300396407, "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:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAQAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////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": 248, "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-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu116", "GPU Enabled": "True", "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 sha256:578b0692efbd9a8249e554a4742a5fa412bb274d6c2bdb6ba648ea72aa52f1a0
|
3 |
+
size 147218
|
ppo-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.6.2
|
ppo-LunarLander-v2/data
ADDED
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 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 0x7f535b1535e0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f535b153670>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f535b153700>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f535b153790>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f535b153820>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f535b1538b0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f535b153940>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f535b1539d0>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f535b153a60>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f535b153af0>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f535b153b80>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f535b149e70>"
|
20 |
+
},
|
21 |
+
"verbose": 1,
|
22 |
+
"policy_kwargs": {},
|
23 |
+
"observation_space": {
|
24 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
25 |
+
":serialized:": "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",
|
26 |
+
"dtype": "float32",
|
27 |
+
"_shape": [
|
28 |
+
8
|
29 |
+
],
|
30 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
31 |
+
"high": "[inf inf inf inf inf inf inf inf]",
|
32 |
+
"bounded_below": "[False False False False False False False False]",
|
33 |
+
"bounded_above": "[False False False False False False False False]",
|
34 |
+
"_np_random": null
|
35 |
+
},
|
36 |
+
"action_space": {
|
37 |
+
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
38 |
+
":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
39 |
+
"n": 4,
|
40 |
+
"_shape": [],
|
41 |
+
"dtype": "int64",
|
42 |
+
"_np_random": null
|
43 |
+
},
|
44 |
+
"n_envs": 16,
|
45 |
+
"num_timesteps": 1015808,
|
46 |
+
"_total_timesteps": 1000000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1670532185300396407,
|
51 |
+
"learning_rate": 0.0003,
|
52 |
+
"tensorboard_log": null,
|
53 |
+
"lr_schedule": {
|
54 |
+
":type:": "<class 'function'>",
|
55 |
+
":serialized:": "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"
|
56 |
+
},
|
57 |
+
"_last_obs": {
|
58 |
+
":type:": "<class 'numpy.ndarray'>",
|
59 |
+
":serialized:": "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"
|
60 |
+
},
|
61 |
+
"_last_episode_starts": {
|
62 |
+
":type:": "<class 'numpy.ndarray'>",
|
63 |
+
":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAQAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
64 |
+
},
|
65 |
+
"_last_original_obs": null,
|
66 |
+
"_episode_num": 0,
|
67 |
+
"use_sde": false,
|
68 |
+
"sde_sample_freq": -1,
|
69 |
+
"_current_progress_remaining": -0.015808000000000044,
|
70 |
+
"ep_info_buffer": {
|
71 |
+
":type:": "<class 'collections.deque'>",
|
72 |
+
":serialized:": "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"
|
73 |
+
},
|
74 |
+
"ep_success_buffer": {
|
75 |
+
":type:": "<class 'collections.deque'>",
|
76 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
+
},
|
78 |
+
"_n_updates": 248,
|
79 |
+
"n_steps": 1024,
|
80 |
+
"gamma": 0.999,
|
81 |
+
"gae_lambda": 0.98,
|
82 |
+
"ent_coef": 0.01,
|
83 |
+
"vf_coef": 0.5,
|
84 |
+
"max_grad_norm": 0.5,
|
85 |
+
"batch_size": 64,
|
86 |
+
"n_epochs": 4,
|
87 |
+
"clip_range": {
|
88 |
+
":type:": "<class 'function'>",
|
89 |
+
":serialized:": "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"
|
90 |
+
},
|
91 |
+
"clip_range_vf": null,
|
92 |
+
"normalize_advantage": true,
|
93 |
+
"target_kl": null
|
94 |
+
}
|
ppo-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c13f9cc665552cbf3f66a6693861821626e2df6d1ba88eb0dc9cac2b2f4840bc
|
3 |
+
size 87929
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:954ede6ffa5ef50257c62de050208a2520c58c2b36ea33307a5b8c6c101fd4be
|
3 |
+
size 43201
|
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-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022
|
2 |
+
Python: 3.8.16
|
3 |
+
Stable-Baselines3: 1.6.2
|
4 |
+
PyTorch: 1.13.0+cu116
|
5 |
+
GPU Enabled: True
|
6 |
+
Numpy: 1.21.6
|
7 |
+
Gym: 0.21.0
|
replay.mp4
ADDED
Binary file (251 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 240.4059264253894, "std_reward": 23.32131374095913, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-08T21:08:13.078134"}
|