MarcusAGray
commited on
Commit
•
8bec5e0
1
Parent(s):
00a0e8d
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: 246.27 +/- 25.88
|
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 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 0x7f6825beac10>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f6825beaca0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f6825bead30>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f6825beadc0>", "_build": "<function ActorCriticPolicy._build at 0x7f6825beae50>", "forward": "<function ActorCriticPolicy.forward at 0x7f6825beaee0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f6825beaf70>", "_predict": "<function ActorCriticPolicy._predict at 0x7f6825be9040>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f6825be90d0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f6825be9160>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f6825be91f0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f6825be5690>"}, "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": 1670347326349903247, "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": 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": "3.8.15", "Stable-Baselines3": "1.6.2", "PyTorch": "1.12.1+cu113", "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:ebf028e359da65ace8102ef447e9b8252450c7d0161251669da2dd4a29c3be3e
|
3 |
+
size 147154
|
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 0x7f6825beac10>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f6825beaca0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f6825bead30>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f6825beadc0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f6825beae50>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f6825beaee0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f6825beaf70>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f6825be9040>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f6825be90d0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f6825be9160>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f6825be91f0>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f6825be5690>"
|
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": 1670347326349903247,
|
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:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////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 sha256:7bae07eb51b0c1b22e19771796ea4abc8dd400751e967529fe1d856727359f8f
|
3 |
+
size 87865
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46fe9b6acd97fdc050c349fa2a00af689409f9ee5d80ff03cfff87ef924f210b
|
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: 3.8.15
|
3 |
+
Stable-Baselines3: 1.6.2
|
4 |
+
PyTorch: 1.12.1+cu113
|
5 |
+
GPU Enabled: True
|
6 |
+
Numpy: 1.21.6
|
7 |
+
Gym: 0.21.0
|
replay.mp4
ADDED
Binary file (253 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 246.27444203854012, "std_reward": 25.880058835710827, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-06T17:55:27.906053"}
|