Terence3927
commited on
Commit
•
4fe2909
1
Parent(s):
e785aa0
Upload best PPO LunarLander-v2 agent (tuned with Optuna).
Browse files- 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
- README.md +37 -0
- config.json +1 -0
- replay.mp4 +0 -0
- results.json +1 -0
PPO-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b89e57d2b8fb2e16810db67ebc080381733b553b0e0bda310f781bc0d769db4a
|
3 |
+
size 146864
|
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 0x7f6ac529c4c0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f6ac529c550>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f6ac529c5e0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f6ac529c670>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f6ac529c700>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f6ac529c790>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f6ac529c820>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f6ac529c8b0>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f6ac529c940>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f6ac529c9d0>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f6ac529ca60>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f6ac5289c90>"
|
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:": "gAWViAAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
39 |
+
"n": 4,
|
40 |
+
"_shape": [],
|
41 |
+
"dtype": "int64",
|
42 |
+
"_np_random": null
|
43 |
+
},
|
44 |
+
"n_envs": 16,
|
45 |
+
"num_timesteps": 1720320,
|
46 |
+
"_total_timesteps": 1711581,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1668051121702691118,
|
51 |
+
"learning_rate": 0.0,
|
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": -0.005105805684919362,
|
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": 525,
|
79 |
+
"n_steps": 1024,
|
80 |
+
"gamma": 0.9974680783123703,
|
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": 5,
|
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 sha256:4430aba46906a7f0854777acce56448eb1beda6d4fc4dd87c7adfd2d02eabeab
|
3 |
+
size 87993
|
PPO-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2ca51c100f55d5af00ca218d0caf4518c5805de30b78b4ed3ae201f8777db84
|
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-5.4.0-124-generic-x86_64-with-glibc2.10 #140-Ubuntu SMP Thu Aug 4 02:23:37 UTC 2022
|
2 |
+
Python: 3.8.13
|
3 |
+
Stable-Baselines3: 1.6.2
|
4 |
+
PyTorch: 1.12.0a0+bd13bc6
|
5 |
+
GPU Enabled: True
|
6 |
+
Numpy: 1.22.3
|
7 |
+
Gym: 0.21.0
|
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: 275.24 +/- 24.12
|
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 0x7f6ac529c4c0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f6ac529c550>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f6ac529c5e0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f6ac529c670>", "_build": "<function ActorCriticPolicy._build at 0x7f6ac529c700>", "forward": "<function ActorCriticPolicy.forward at 0x7f6ac529c790>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f6ac529c820>", "_predict": "<function ActorCriticPolicy._predict at 0x7f6ac529c8b0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f6ac529c940>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f6ac529c9d0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f6ac529ca60>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f6ac5289c90>"}, "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:": "gAWViAAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 1720320, "_total_timesteps": 1711581, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1668051121702691118, "learning_rate": 0.0, "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": -0.005105805684919362, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 525, "n_steps": 1024, "gamma": 0.9974680783123703, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 5, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.4.0-124-generic-x86_64-with-glibc2.10 #140-Ubuntu SMP Thu Aug 4 02:23:37 UTC 2022", "Python": "3.8.13", "Stable-Baselines3": "1.6.2", "PyTorch": "1.12.0a0+bd13bc6", "GPU Enabled": "True", "Numpy": "1.22.3", "Gym": "0.21.0"}}
|
replay.mp4
ADDED
Binary file (216 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 275.239142264037, "std_reward": 24.11826424770404, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-11-10T05:17:39.354989"}
|