Upload PPO LunarLander-v2 trained agent
Browse files- README.md +37 -0
- config.json +1 -0
- my_ppo_rl_lunarlander.zip +3 -0
- my_ppo_rl_lunarlander/_stable_baselines3_version +1 -0
- my_ppo_rl_lunarlander/data +95 -0
- my_ppo_rl_lunarlander/policy.optimizer.pth +3 -0
- my_ppo_rl_lunarlander/policy.pth +3 -0
- my_ppo_rl_lunarlander/pytorch_variables.pth +3 -0
- my_ppo_rl_lunarlander/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: 245.64 +/- 23.52
|
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 0x7f346ca008b0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f346ca00940>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f346ca009d0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f346ca00a60>", "_build": "<function ActorCriticPolicy._build at 0x7f346ca00af0>", "forward": "<function ActorCriticPolicy.forward at 0x7f346ca00b80>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f346ca00c10>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f346ca00ca0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f346ca00d30>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f346ca00dc0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f346ca00e50>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f346ca00ee0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f346c9fd510>"}, "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:": "gAWVgQAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwFc2hhcGWUKYwFZHR5cGWUjAVudW1weZRoB5OUjAJpOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRijApfbnBfcmFuZG9tlE51Yi4=", "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": 1673432675104901037, "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:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAABAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////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-glibc2.27 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.0+cu116", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.17.3"}}
|
my_ppo_rl_lunarlander.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a2c754f847b8e6303595b1c713c14262b829fd296518b88875da0fecea97b04a
|
3 |
+
size 147414
|
my_ppo_rl_lunarlander/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.7.0
|
my_ppo_rl_lunarlander/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 0x7f346ca008b0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f346ca00940>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f346ca009d0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f346ca00a60>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f346ca00af0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f346ca00b80>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f346ca00c10>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f346ca00ca0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f346ca00d30>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f346ca00dc0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f346ca00e50>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f346ca00ee0>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc_data object at 0x7f346c9fd510>"
|
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:": "gAWVgQAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwFc2hhcGWUKYwFZHR5cGWUjAVudW1weZRoB5OUjAJpOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRijApfbnBfcmFuZG9tlE51Yi4=",
|
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": 1673432675104901037,
|
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:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAABAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////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:": "gAWVwQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAEsBSwFLE0MEiABTAJROhZQpjAFflIWUjEgvdXNyL2xvY2FsL2xpYi9weXRob24zLjgvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuCQwIAAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEgvdXNyL2xvY2FsL2xpYi9weXRob24zLjgvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpSMHGNsb3VkcGlja2xlLmNsb3VkcGlja2xlX2Zhc3SUjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoIH2UfZQoaBdoDowMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBiMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHP8mZmZmZmZqFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="
|
91 |
+
},
|
92 |
+
"clip_range_vf": null,
|
93 |
+
"normalize_advantage": true,
|
94 |
+
"target_kl": null
|
95 |
+
}
|
my_ppo_rl_lunarlander/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a932ae5f7088338f17dec593455aa3fde6e3a2489c0acc533c2f075a35cd916
|
3 |
+
size 87929
|
my_ppo_rl_lunarlander/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a1d3f016942c8535fb67c011b34e33385fc01fa033253a4dff50036fcc75f1de
|
3 |
+
size 43393
|
my_ppo_rl_lunarlander/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
|
3 |
+
size 431
|
my_ppo_rl_lunarlander/system_info.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: Linux-5.10.147+-x86_64-with-glibc2.27 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
|
2 |
+
- Python: 3.8.16
|
3 |
+
- Stable-Baselines3: 1.7.0
|
4 |
+
- PyTorch: 1.13.0+cu116
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.21.6
|
7 |
+
- Gym: 0.17.3
|
replay.mp4
ADDED
Binary file (199 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 245.64081706951373, "std_reward": 23.52389959054624, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-11T10:53:31.283094"}
|