michaelowens
commited on
Commit
•
913fb1c
1
Parent(s):
2931228
Hi!
Browse files- 128wide2e6steps.zip +3 -0
- 128wide2e6steps/_stable_baselines3_version +1 -0
- 128wide2e6steps/data +108 -0
- 128wide2e6steps/policy.optimizer.pth +3 -0
- 128wide2e6steps/policy.pth +3 -0
- 128wide2e6steps/pytorch_variables.pth +3 -0
- 128wide2e6steps/system_info.txt +7 -0
- README.md +37 -0
- config.json +1 -0
- replay.mp4 +0 -0
- results.json +1 -0
128wide2e6steps.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea8b40bf82d7a623d95d9107770c6073ca214cc8c9721827a5725f4f4e27aa0b
|
3 |
+
size 846419
|
128wide2e6steps/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.6.2
|
128wide2e6steps/data
ADDED
@@ -0,0 +1,108 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 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 0x7f4f5b873ca0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f4f5b873d30>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f4f5b873dc0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f4f5b873e50>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f4f5b873ee0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f4f5b873f70>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f4f5b877040>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f4f5b8770d0>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f4f5b877160>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f4f5b8771f0>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f4f5b877280>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f4f5b870510>"
|
20 |
+
},
|
21 |
+
"verbose": 1,
|
22 |
+
"policy_kwargs": {
|
23 |
+
"net_arch": [
|
24 |
+
128,
|
25 |
+
{
|
26 |
+
"pi": [
|
27 |
+
128,
|
28 |
+
128
|
29 |
+
],
|
30 |
+
"vf": [
|
31 |
+
128,
|
32 |
+
128
|
33 |
+
]
|
34 |
+
}
|
35 |
+
]
|
36 |
+
},
|
37 |
+
"observation_space": {
|
38 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
39 |
+
":serialized:": "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",
|
40 |
+
"dtype": "float32",
|
41 |
+
"_shape": [
|
42 |
+
8
|
43 |
+
],
|
44 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
45 |
+
"high": "[inf inf inf inf inf inf inf inf]",
|
46 |
+
"bounded_below": "[False False False False False False False False]",
|
47 |
+
"bounded_above": "[False False False False False False False False]",
|
48 |
+
"_np_random": null
|
49 |
+
},
|
50 |
+
"action_space": {
|
51 |
+
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
52 |
+
":serialized:": "gAWViAAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
53 |
+
"n": 4,
|
54 |
+
"_shape": [],
|
55 |
+
"dtype": "int64",
|
56 |
+
"_np_random": null
|
57 |
+
},
|
58 |
+
"n_envs": 16,
|
59 |
+
"num_timesteps": 1015808,
|
60 |
+
"_total_timesteps": 1000000,
|
61 |
+
"_num_timesteps_at_start": 0,
|
62 |
+
"seed": null,
|
63 |
+
"action_noise": null,
|
64 |
+
"start_time": 1671505305770078574,
|
65 |
+
"learning_rate": 0.0003,
|
66 |
+
"tensorboard_log": null,
|
67 |
+
"lr_schedule": {
|
68 |
+
":type:": "<class 'function'>",
|
69 |
+
":serialized:": "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"
|
70 |
+
},
|
71 |
+
"_last_obs": {
|
72 |
+
":type:": "<class 'numpy.ndarray'>",
|
73 |
+
":serialized:": "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"
|
74 |
+
},
|
75 |
+
"_last_episode_starts": {
|
76 |
+
":type:": "<class 'numpy.ndarray'>",
|
77 |
+
":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
78 |
+
},
|
79 |
+
"_last_original_obs": null,
|
80 |
+
"_episode_num": 0,
|
81 |
+
"use_sde": false,
|
82 |
+
"sde_sample_freq": -1,
|
83 |
+
"_current_progress_remaining": -0.015808000000000044,
|
84 |
+
"ep_info_buffer": {
|
85 |
+
":type:": "<class 'collections.deque'>",
|
86 |
+
":serialized:": "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"
|
87 |
+
},
|
88 |
+
"ep_success_buffer": {
|
89 |
+
":type:": "<class 'collections.deque'>",
|
90 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
91 |
+
},
|
92 |
+
"_n_updates": 496,
|
93 |
+
"n_steps": 1024,
|
94 |
+
"gamma": 0.999,
|
95 |
+
"gae_lambda": 0.98,
|
96 |
+
"ent_coef": 0.01,
|
97 |
+
"vf_coef": 0.5,
|
98 |
+
"max_grad_norm": 0.5,
|
99 |
+
"batch_size": 64,
|
100 |
+
"n_epochs": 4,
|
101 |
+
"clip_range": {
|
102 |
+
":type:": "<class 'function'>",
|
103 |
+
":serialized:": "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"
|
104 |
+
},
|
105 |
+
"clip_range_vf": null,
|
106 |
+
"normalize_advantage": true,
|
107 |
+
"target_kl": null
|
108 |
+
}
|
128wide2e6steps/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7fe4b4c05e5f7eb5d8beb360c0667177dfb73510538ee5d0a8fc0fcf5db9e58
|
3 |
+
size 554087
|
128wide2e6steps/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:73121a19f2b17c2b648704400f76199b91bf277d66d22946b8c8b2405ee373bc
|
3 |
+
size 276091
|
128wide2e6steps/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
|
3 |
+
size 431
|
128wide2e6steps/system_info.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
OS: Linux-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022
|
2 |
+
Python: 3.8.16
|
3 |
+
Stable-Baselines3: 1.6.2
|
4 |
+
PyTorch: 1.13.0+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: 275.62 +/- 20.28
|
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 sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\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 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 0x7f4f5b873ca0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f4f5b873d30>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f4f5b873dc0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f4f5b873e50>", "_build": "<function ActorCriticPolicy._build at 0x7f4f5b873ee0>", "forward": "<function ActorCriticPolicy.forward at 0x7f4f5b873f70>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f4f5b877040>", "_predict": "<function ActorCriticPolicy._predict at 0x7f4f5b8770d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f4f5b877160>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f4f5b8771f0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f4f5b877280>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f4f5b870510>"}, "verbose": 1, "policy_kwargs": {"net_arch": [128, {"pi": [128, 128], "vf": [128, 128]}]}, "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, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1671505305770078574, "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": 496, "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-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu116", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
|
replay.mp4
ADDED
Binary file (222 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 275.61709010601277, "std_reward": 20.276737855534325, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-20T08:49:17.743977"}
|