Upload PPO LunarLander-v2 trained agent
Browse files- README.md +37 -0
- config.json +1 -0
- replay.mp4 +0 -0
- results.json +1 -0
- unit1-ppo-LunarLander-v2.zip +3 -0
- unit1-ppo-LunarLander-v2/_stable_baselines3_version +1 -0
- unit1-ppo-LunarLander-v2/data +95 -0
- unit1-ppo-LunarLander-v2/policy.optimizer.pth +3 -0
- unit1-ppo-LunarLander-v2/policy.pth +3 -0
- unit1-ppo-LunarLander-v2/pytorch_variables.pth +3 -0
- unit1-ppo-LunarLander-v2/system_info.txt +7 -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: -161.94 +/- 30.35
|
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 0x7f26970ecdc0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f26970ece50>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f26970ecee0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f26970ecf70>", "_build": "<function ActorCriticPolicy._build at 0x7f26970f2040>", "forward": "<function ActorCriticPolicy.forward at 0x7f26970f20d0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f26970f2160>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f26970f21f0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f26970f2280>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f26970f2310>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f26970f23a0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f26970f2430>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f26970efe40>"}, "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": 114688, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1678359367444183457, "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": -0.1468799999999999, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 28, "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"}}
|
replay.mp4
ADDED
Binary file (231 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": -161.94492785872427, "std_reward": 30.35180427751088, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-09T11:00:27.843679"}
|
unit1-ppo-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a76c2d95827e5ea6de872a4efb7ee8723c1e199701c4dc0ce95407437506e7e
|
3 |
+
size 147292
|
unit1-ppo-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.7.0
|
unit1-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 0x7f26970ecdc0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f26970ece50>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f26970ecee0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f26970ecf70>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f26970f2040>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f26970f20d0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f26970f2160>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f26970f21f0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f26970f2280>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f26970f2310>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f26970f23a0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f26970f2430>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7f26970efe40>"
|
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": 114688,
|
47 |
+
"_total_timesteps": 100000,
|
48 |
+
"_num_timesteps_at_start": 0,
|
49 |
+
"seed": null,
|
50 |
+
"action_noise": null,
|
51 |
+
"start_time": 1678359367444183457,
|
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": -0.1468799999999999,
|
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": 28,
|
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 |
+
}
|
unit1-ppo-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0794e1e8c88f74f29596657f992747e2ee76576985354914a8edd257d23dbd7a
|
3 |
+
size 87929
|
unit1-ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8cf163be54ed9928be1a5c3ccf4f6eeaaeb5090e4ee3d1bb2ecdc7f8e4088551
|
3 |
+
size 43393
|
unit1-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
|
unit1-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
|