Initial commit of PPO model for LunarLander-v2
Browse files- LunarLander_PPO.zip +3 -0
- LunarLander_PPO/_stable_baselines3_version +1 -0
- LunarLander_PPO/data +95 -0
- LunarLander_PPO/policy.optimizer.pth +3 -0
- LunarLander_PPO/policy.pth +3 -0
- LunarLander_PPO/pytorch_variables.pth +3 -0
- LunarLander_PPO/system_info.txt +7 -0
- README.md +37 -0
- config.json +1 -0
- replay.mp4 +0 -0
- results.json +1 -0
LunarLander_PPO.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e30818171e8c6317037e0d6bec9aa088fdc05752c6821eb71bfe2a6297b52d11
|
3 |
+
size 147335
|
LunarLander_PPO/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.7.0
|
LunarLander_PPO/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 0x7f582325ad30>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f582325adc0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f582325ae50>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f582325aee0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f582325af70>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f582325e040>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f582325e0d0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f582325e160>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f582325e1f0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f582325e280>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f582325e310>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f582325e3a0>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc_data object at 0x7f5823254c90>"
|
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": 1677012584006071904,
|
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": 380,
|
80 |
+
"n_steps": 2048,
|
81 |
+
"gamma": 0.99,
|
82 |
+
"gae_lambda": 0.95,
|
83 |
+
"ent_coef": 0.0,
|
84 |
+
"vf_coef": 0.5,
|
85 |
+
"max_grad_norm": 0.5,
|
86 |
+
"batch_size": 64,
|
87 |
+
"n_epochs": 10,
|
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 |
+
}
|
LunarLander_PPO/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7dbc0f9acbf1e2c4062e73a80159525742fc09c08a2e0b905e208bba155fb55
|
3 |
+
size 87929
|
LunarLander_PPO/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a992ade5a5911cd08a4227f98dff97208c83d958ca62246c67c79e86ddcce2b
|
3 |
+
size 43393
|
LunarLander_PPO/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
|
3 |
+
size 431
|
LunarLander_PPO/system_info.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: Linux-5.10.147+-x86_64-with-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
|
2 |
+
- Python: 3.8.10
|
3 |
+
- Stable-Baselines3: 1.7.0
|
4 |
+
- PyTorch: 1.13.1+cu116
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.21.6
|
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: 256.07 +/- 22.91
|
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 0x7f582325ad30>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f582325adc0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f582325ae50>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f582325aee0>", "_build": "<function ActorCriticPolicy._build at 0x7f582325af70>", "forward": "<function ActorCriticPolicy.forward at 0x7f582325e040>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f582325e0d0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f582325e160>", "_predict": "<function ActorCriticPolicy._predict at 0x7f582325e1f0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f582325e280>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f582325e310>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f582325e3a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f5823254c90>"}, "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": 1677012584006071904, "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": 380, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "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-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.8.10", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu116", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
|
replay.mp4
ADDED
Binary file (182 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 256.06955964165616, "std_reward": 22.914370368012932, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-21T21:40:51.116807"}
|