course_unit1
Browse files- .gitattributes +1 -0
- README.md +36 -0
- config.json +1 -0
- ppo-LunarLander-v2.zip +3 -0
- ppo-LunarLander-v2/_stable_baselines3_version +1 -0
- ppo-LunarLander-v2/data +94 -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 +3 -0
- results.json +1 -0
.gitattributes
CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.mp4 filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
- metrics:
|
12 |
+
- type: mean_reward
|
13 |
+
value: 201.47 +/- 16.84
|
14 |
+
name: mean_reward
|
15 |
+
task:
|
16 |
+
type: reinforcement-learning
|
17 |
+
name: reinforcement-learning
|
18 |
+
dataset:
|
19 |
+
name: LunarLander-v2
|
20 |
+
type: LunarLander-v2
|
21 |
+
---
|
22 |
+
|
23 |
+
# **PPO** Agent playing **LunarLander-v2**
|
24 |
+
This is a trained model of a **PPO** agent playing **LunarLander-v2**
|
25 |
+
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
26 |
+
|
27 |
+
## Usage (with Stable-baselines3)
|
28 |
+
TODO: Add your code
|
29 |
+
|
30 |
+
|
31 |
+
```python
|
32 |
+
from stable_baselines3 import ...
|
33 |
+
from huggingface_sb3 import load_from_hub
|
34 |
+
|
35 |
+
...
|
36 |
+
```
|
config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__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 0x7f1683bab560>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f1683bab5f0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f1683bab680>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f1683bab710>", "_build": "<function ActorCriticPolicy._build at 0x7f1683bab7a0>", "forward": "<function ActorCriticPolicy.forward at 0x7f1683bab830>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f1683bab8c0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f1683bab950>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f1683bab9e0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f1683baba70>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f1683babb00>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f1683b778a0>"}, "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:": "gASVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 507904, "_total_timesteps": 500000.0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1654434659.3059483, "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:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="}, "_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:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 124, "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-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022", "Python": "3.7.13", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
|
ppo-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f4612c0c59f29886076d1066ad80728c2f59cac251f48ecc42fde51a8114f7d
|
3 |
+
size 144158
|
ppo-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.5.0
|
ppo-LunarLander-v2/data
ADDED
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"policy_class": {
|
3 |
+
":type:": "<class 'abc.ABCMeta'>",
|
4 |
+
":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
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 0x7f1683bab560>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f1683bab5f0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f1683bab680>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f1683bab710>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f1683bab7a0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f1683bab830>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f1683bab8c0>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f1683bab950>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f1683bab9e0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f1683baba70>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f1683babb00>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f1683b778a0>"
|
20 |
+
},
|
21 |
+
"verbose": 1,
|
22 |
+
"policy_kwargs": {},
|
23 |
+
"observation_space": {
|
24 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
25 |
+
":serialized:": "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",
|
26 |
+
"dtype": "float32",
|
27 |
+
"_shape": [
|
28 |
+
8
|
29 |
+
],
|
30 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
31 |
+
"high": "[inf inf inf inf inf inf inf inf]",
|
32 |
+
"bounded_below": "[False False False False False False False False]",
|
33 |
+
"bounded_above": "[False False False False False False False False]",
|
34 |
+
"_np_random": null
|
35 |
+
},
|
36 |
+
"action_space": {
|
37 |
+
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
38 |
+
":serialized:": "gASVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
39 |
+
"n": 4,
|
40 |
+
"_shape": [],
|
41 |
+
"dtype": "int64",
|
42 |
+
"_np_random": null
|
43 |
+
},
|
44 |
+
"n_envs": 16,
|
45 |
+
"num_timesteps": 507904,
|
46 |
+
"_total_timesteps": 500000.0,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1654434659.3059483,
|
51 |
+
"learning_rate": 0.0003,
|
52 |
+
"tensorboard_log": null,
|
53 |
+
"lr_schedule": {
|
54 |
+
":type:": "<class 'function'>",
|
55 |
+
":serialized:": "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"
|
56 |
+
},
|
57 |
+
"_last_obs": {
|
58 |
+
":type:": "<class 'numpy.ndarray'>",
|
59 |
+
":serialized:": "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"
|
60 |
+
},
|
61 |
+
"_last_episode_starts": {
|
62 |
+
":type:": "<class 'numpy.ndarray'>",
|
63 |
+
":serialized:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="
|
64 |
+
},
|
65 |
+
"_last_original_obs": null,
|
66 |
+
"_episode_num": 0,
|
67 |
+
"use_sde": false,
|
68 |
+
"sde_sample_freq": -1,
|
69 |
+
"_current_progress_remaining": -0.015808000000000044,
|
70 |
+
"ep_info_buffer": {
|
71 |
+
":type:": "<class 'collections.deque'>",
|
72 |
+
":serialized:": "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"
|
73 |
+
},
|
74 |
+
"ep_success_buffer": {
|
75 |
+
":type:": "<class 'collections.deque'>",
|
76 |
+
":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
+
},
|
78 |
+
"_n_updates": 124,
|
79 |
+
"n_steps": 1024,
|
80 |
+
"gamma": 0.999,
|
81 |
+
"gae_lambda": 0.98,
|
82 |
+
"ent_coef": 0.01,
|
83 |
+
"vf_coef": 0.5,
|
84 |
+
"max_grad_norm": 0.5,
|
85 |
+
"batch_size": 64,
|
86 |
+
"n_epochs": 4,
|
87 |
+
"clip_range": {
|
88 |
+
":type:": "<class 'function'>",
|
89 |
+
":serialized:": "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"
|
90 |
+
},
|
91 |
+
"clip_range_vf": null,
|
92 |
+
"normalize_advantage": true,
|
93 |
+
"target_kl": null
|
94 |
+
}
|
ppo-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d88853eec0f275511e9327fbca9958caa9a46493c62a00d57500647ef70f5973
|
3 |
+
size 84829
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:567d4ad5db86c34b18c3e076ce895bb9b003b6473cd26bee7d8d591a66740f7f
|
3 |
+
size 43201
|
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-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022
|
2 |
+
Python: 3.7.13
|
3 |
+
Stable-Baselines3: 1.5.0
|
4 |
+
PyTorch: 1.11.0+cu113
|
5 |
+
GPU Enabled: True
|
6 |
+
Numpy: 1.21.6
|
7 |
+
Gym: 0.21.0
|
replay.mp4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d9f617bbe6719bf4cc4baf42ce1eff124b47544700a552c2403b82f3c9e01cdf
|
3 |
+
size 267092
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 201.47189519541354, "std_reward": 16.837371196259966, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-05T13:46:19.708040"}
|