Commit
•
1e70e2e
1
Parent(s):
6292947
Uploading PPO LunarLanderv2 agent
Browse files- README.md +37 -0
- config.json +1 -0
- ppo-LunarLander-v2_2.zip +3 -0
- ppo-LunarLander-v2_2/_stable_baselines3_version +1 -0
- ppo-LunarLander-v2_2/data +96 -0
- ppo-LunarLander-v2_2/policy.optimizer.pth +3 -0
- ppo-LunarLander-v2_2/policy.pth +3 -0
- ppo-LunarLander-v2_2/pytorch_variables.pth +3 -0
- ppo-LunarLander-v2_2/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_MLP
|
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: 235.61 +/- 64.54
|
20 |
+
name: mean_reward
|
21 |
+
verified: false
|
22 |
+
---
|
23 |
+
|
24 |
+
# **PPO_MLP** Agent playing **LunarLander-v2**
|
25 |
+
This is a trained model of a **PPO_MLP** 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 0x7f55a5245000>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f55a5245090>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f55a5245120>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f55a52451b0>", "_build": "<function ActorCriticPolicy._build at 0x7f55a5245240>", "forward": "<function ActorCriticPolicy.forward at 0x7f55a52452d0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f55a5245360>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f55a52453f0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f55a5245480>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f55a5245510>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f55a52455a0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f55a5245630>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f55a523a5c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 16384, "_total_timesteps": 100.0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1683378997592620749, "learning_rate": 0.0003, "tensorboard_log": "./ppo_lunar_lander_v2/", "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": -162.84, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 252, "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, "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, "system_info": {"OS": "Linux-5.10.147+-x86_64-with-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.10.11", "Stable-Baselines3": "1.8.0", "PyTorch": "2.0.0+cu118", "GPU Enabled": "True", "Numpy": "1.24.3", "Gym": "0.21.0"}}
|
ppo-LunarLander-v2_2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:743b65877153323ed4ce92363cd4f9de143932ea795cb51f1bebc29921e5b59b
|
3 |
+
size 143386
|
ppo-LunarLander-v2_2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.8.0
|
ppo-LunarLander-v2_2/data
ADDED
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 0x7f55a5245000>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f55a5245090>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f55a5245120>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f55a52451b0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f55a5245240>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f55a52452d0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f55a5245360>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f55a52453f0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f55a5245480>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f55a5245510>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f55a52455a0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f55a5245630>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7f55a523a5c0>"
|
21 |
+
},
|
22 |
+
"verbose": 1,
|
23 |
+
"policy_kwargs": {},
|
24 |
+
"num_timesteps": 16384,
|
25 |
+
"_total_timesteps": 100.0,
|
26 |
+
"_num_timesteps_at_start": 0,
|
27 |
+
"seed": null,
|
28 |
+
"action_noise": null,
|
29 |
+
"start_time": 1683378997592620749,
|
30 |
+
"learning_rate": 0.0003,
|
31 |
+
"tensorboard_log": "./ppo_lunar_lander_v2/",
|
32 |
+
"lr_schedule": {
|
33 |
+
":type:": "<class 'function'>",
|
34 |
+
":serialized:": "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"
|
35 |
+
},
|
36 |
+
"_last_obs": {
|
37 |
+
":type:": "<class 'numpy.ndarray'>",
|
38 |
+
":serialized:": "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"
|
39 |
+
},
|
40 |
+
"_last_episode_starts": {
|
41 |
+
":type:": "<class 'numpy.ndarray'>",
|
42 |
+
":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
43 |
+
},
|
44 |
+
"_last_original_obs": null,
|
45 |
+
"_episode_num": 0,
|
46 |
+
"use_sde": false,
|
47 |
+
"sde_sample_freq": -1,
|
48 |
+
"_current_progress_remaining": -162.84,
|
49 |
+
"_stats_window_size": 100,
|
50 |
+
"ep_info_buffer": {
|
51 |
+
":type:": "<class 'collections.deque'>",
|
52 |
+
":serialized:": "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"
|
53 |
+
},
|
54 |
+
"ep_success_buffer": {
|
55 |
+
":type:": "<class 'collections.deque'>",
|
56 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
57 |
+
},
|
58 |
+
"_n_updates": 252,
|
59 |
+
"n_steps": 1024,
|
60 |
+
"gamma": 0.999,
|
61 |
+
"gae_lambda": 0.98,
|
62 |
+
"ent_coef": 0.01,
|
63 |
+
"vf_coef": 0.5,
|
64 |
+
"max_grad_norm": 0.5,
|
65 |
+
"batch_size": 64,
|
66 |
+
"n_epochs": 4,
|
67 |
+
"clip_range": {
|
68 |
+
":type:": "<class 'function'>",
|
69 |
+
":serialized:": "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"
|
70 |
+
},
|
71 |
+
"clip_range_vf": null,
|
72 |
+
"normalize_advantage": true,
|
73 |
+
"target_kl": null,
|
74 |
+
"observation_space": {
|
75 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
76 |
+
":serialized:": "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",
|
77 |
+
"dtype": "float32",
|
78 |
+
"_shape": [
|
79 |
+
8
|
80 |
+
],
|
81 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
82 |
+
"high": "[inf inf inf inf inf inf inf inf]",
|
83 |
+
"bounded_below": "[False False False False False False False False]",
|
84 |
+
"bounded_above": "[False False False False False False False False]",
|
85 |
+
"_np_random": null
|
86 |
+
},
|
87 |
+
"action_space": {
|
88 |
+
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
89 |
+
":serialized:": "gAWViAAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
90 |
+
"n": 4,
|
91 |
+
"_shape": [],
|
92 |
+
"dtype": "int64",
|
93 |
+
"_np_random": null
|
94 |
+
},
|
95 |
+
"n_envs": 16
|
96 |
+
}
|
ppo-LunarLander-v2_2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68d47558fc6907b47ae02aa76c32346880adf214f14de7a8f8759a089615f4ae
|
3 |
+
size 88057
|
ppo-LunarLander-v2_2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae208e9820f48f8930fa592e1989f85d4ead5f0c090e225c7ba102975e154386
|
3 |
+
size 43329
|
ppo-LunarLander-v2_2/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_2/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: 3.10.11
|
3 |
+
- Stable-Baselines3: 1.8.0
|
4 |
+
- PyTorch: 2.0.0+cu118
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.24.3
|
7 |
+
- Gym: 0.21.0
|
replay.mp4
ADDED
Binary file (243 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 235.60539408270733, "std_reward": 64.5350551843906, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-05-06T13:36:51.896235"}
|