MahdiMasoon
commited on
Commit
·
f197a85
1
Parent(s):
4b3ff2c
initial
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: base
|
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: 219.91 +/- 18.33
|
20 |
+
name: mean_reward
|
21 |
+
verified: false
|
22 |
+
---
|
23 |
+
|
24 |
+
# **base** Agent playing **LunarLander-v2**
|
25 |
+
This is a trained model of a **base** 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 0x7f736ca22790>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f736ca22820>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f736ca228b0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f736ca22940>", "_build": "<function ActorCriticPolicy._build at 0x7f736ca229d0>", "forward": "<function ActorCriticPolicy.forward at 0x7f736ca22a60>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f736ca22af0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f736ca22b80>", "_predict": "<function ActorCriticPolicy._predict at 0x7f736ca22c10>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f736ca22ca0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f736ca22d30>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f736ca22dc0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f736ca243c0>"}, "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": 1678818877725697478, "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": 256, "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 sha256:56d870391ff864826f777f2515e1bda9de90fa5321cea638527545083307af00
|
3 |
+
size 147430
|
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 0x7f736ca22790>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f736ca22820>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f736ca228b0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f736ca22940>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f736ca229d0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f736ca22a60>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f736ca22af0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f736ca22b80>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f736ca22c10>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f736ca22ca0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f736ca22d30>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f736ca22dc0>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7f736ca243c0>"
|
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": 1678818877725697478,
|
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:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAABbqbL6um7q6Rtr9Oi8d/jbimew7QOEWugAAgD8AAIA/OsVoPvXghT97z44+ohW6vsxlpT5rILK8AAAAAAAAAAAa7969w00PurPw8rqrBck0oAZ+u/eNDToAAIA/AAAAABpHAb5qo5E/Mo2yvbSwWb6GjEa8JU9PPQAAAAAAAAAAM/rDPFwvDbqqLyw5slgeNq8JaLvr+0q4AACAPwAAgD/mjpQ9rkftuPoGmjpNB1Y1Smlvu8Y5tbkAAIA/AACAP81sabquZ6+4Zfu6Oz4uPbUCcc87A6BNtAAAgD8AAIA/hhwdPsMFBrwSzhY7EBFauasdhL1tOTW6AACAPwAAgD8A0+m82sCKP+3ivr2gc1++f6q3vZmgCL0AAAAAAAAAADMCZj0f/bS5+ILmOma0ArXxZs67DhMJugAAgD8AAIA/5sC7vSN6qj4Kihw9zpGFvp9IBzzt+c28AAAAAAAAAAAAIs08H4W3uR1o3rrHwgS236IOOxOaADoAAIA/AACAPwCSpD0U2py6gJzTOsTC0zVeKwE7yAT0uQAAgD8AAIA/ZrA3PbgWtLlOLJO6Eb6PtZq2w7mVBKs5AACAPwAAgD+AYXW9PckyPvN4zz3V3uq9K5ymvdnVirwAAAAAAAAAAJq5yjuU0ag+Ae21PYIxcb6vp4M9Qy3VPQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="
|
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": 256,
|
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 sha256:9f177acee915ba45edbdc8f5b0e20893ac8b3fe42974442a6d65c96444001d83
|
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:f2520c5546a15ed68d5e8e3b6f75bfbfef57075c534a35000930a5c0816f5922
|
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 (252 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 219.9052491535587, "std_reward": 18.333196389542103, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-14T19:11:26.862460"}
|