pelinbalci
commited on
Commit
•
d7872d9
1
Parent(s):
4d66405
Push LunarLander-v2 model
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 +95 -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: 260.94 +/- 16.33
|
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 0x7f88bb2474c0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f88bb247550>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f88bb2475e0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f88bb247670>", "_build": "<function ActorCriticPolicy._build at 0x7f88bb247700>", "forward": "<function ActorCriticPolicy.forward at 0x7f88bb247790>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f88bb247820>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f88bb2478b0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f88bb247940>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f88bb2479d0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f88bb247a60>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f88bb247af0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f88bb245b40>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "gAWVnwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLCIWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAAAAAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/5RoCksIhZSMAUOUdJRSlIwEaGlnaJRoEiiWIAAAAAAAAAAAAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAf5RoCksIhZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolggAAAAAAAAAAAAAAAAAAACUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLCIWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYIAAAAAAAAAAAAAAAAAAAAlGghSwiFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu", "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": 1680187556879184571, "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-5.10.147+-x86_64-with-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.9.16", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu116", "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 sha256:07cc69804803ad4004e4c9406c84b32b14e5193ca3e31824f109b4bee39ad034
|
3 |
+
size 147425
|
ppo_LunarLander_v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.7.0
|
ppo_LunarLander_v2/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 0x7f88bb2474c0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f88bb247550>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f88bb2475e0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f88bb247670>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f88bb247700>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f88bb247790>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f88bb247820>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f88bb2478b0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f88bb247940>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f88bb2479d0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f88bb247a60>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f88bb247af0>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7f88bb245b40>"
|
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": 1680187556879184571,
|
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": 248,
|
80 |
+
"n_steps": 1024,
|
81 |
+
"gamma": 0.999,
|
82 |
+
"gae_lambda": 0.98,
|
83 |
+
"ent_coef": 0.01,
|
84 |
+
"vf_coef": 0.5,
|
85 |
+
"max_grad_norm": 0.5,
|
86 |
+
"batch_size": 64,
|
87 |
+
"n_epochs": 4,
|
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_v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1fa368b086787279113c560595ca7b46e259ad869ae8cc6f886ab1c0e2c2512c
|
3 |
+
size 87929
|
ppo_LunarLander_v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4aac19278cfdf2e1adc7ccb6fa10fdb4fe6bdd80e3243e6400d89e38b9410be3
|
3 |
+
size 43393
|
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: 1.7.0
|
4 |
+
- PyTorch: 1.13.1+cu116
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.22.4
|
7 |
+
- Gym: 0.21.0
|
replay.mp4
ADDED
Binary file (227 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 260.9369695328561, "std_reward": 16.333570537932392, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-30T15:31:13.619936"}
|