Commit
•
4efefa4
1
Parent(s):
7a25032
first model solution
Browse files- LunarLander-v2-solution.zip +3 -0
- LunarLander-v2-solution/_stable_baselines3_version +1 -0
- LunarLander-v2-solution/data +95 -0
- LunarLander-v2-solution/policy.optimizer.pth +3 -0
- LunarLander-v2-solution/policy.pth +3 -0
- LunarLander-v2-solution/pytorch_variables.pth +3 -0
- LunarLander-v2-solution/system_info.txt +7 -0
- README.md +37 -0
- config.json +1 -0
- results.json +1 -0
LunarLander-v2-solution.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e272af46cdd048d875b64e2481782ec819206ec5f2c0ae010a139c9eaa637aab
|
3 |
+
size 147517
|
LunarLander-v2-solution/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.7.0
|
LunarLander-v2-solution/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 0x7fce3c3f00d0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fce3c3f0160>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fce3c3f01f0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fce3c3f0280>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fce3c3f0310>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fce3c3f03a0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7fce3c3f0430>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fce3c3f04c0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fce3c3f0550>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fce3c3f05e0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fce3c3f0670>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fce3c3f0700>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7fce3c3ed780>"
|
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": 1676191113176024881,
|
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": -0.015808000000000044,
|
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": 310,
|
80 |
+
"n_steps": 2048,
|
81 |
+
"gamma": 0.99,
|
82 |
+
"gae_lambda": 0.95,
|
83 |
+
"ent_coef": 0.0,
|
84 |
+
"vf_coef": 0.5,
|
85 |
+
"max_grad_norm": 0.5,
|
86 |
+
"batch_size": 64,
|
87 |
+
"n_epochs": 10,
|
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 |
+
}
|
LunarLander-v2-solution/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a2b4f23aaa7ca4306fca4a7b055ad1356b6472bfb96d4a680f4756197227761
|
3 |
+
size 87929
|
LunarLander-v2-solution/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac64cdf32cc48fe9a5bef003e2225752072747e8d8b945b8a474c9664566a3f7
|
3 |
+
size 43393
|
LunarLander-v2-solution/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
|
3 |
+
size 431
|
LunarLander-v2-solution/system_info.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: Linux-6.1.10-060110-generic-x86_64-with-glibc2.36 # 202302060840 SMP PREEMPT_DYNAMIC Mon Feb 6 09:32:56 UTC 2023
|
2 |
+
- Python: 3.10.9
|
3 |
+
- Stable-Baselines3: 1.7.0
|
4 |
+
- PyTorch: 1.13.1
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.23.5
|
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: 240.37 +/- 37.94
|
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 0x7fce3c3f00d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fce3c3f0160>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fce3c3f01f0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fce3c3f0280>", "_build": "<function ActorCriticPolicy._build at 0x7fce3c3f0310>", "forward": "<function ActorCriticPolicy.forward at 0x7fce3c3f03a0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fce3c3f0430>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fce3c3f04c0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fce3c3f0550>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fce3c3f05e0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fce3c3f0670>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fce3c3f0700>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fce3c3ed780>"}, "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": 1676191113176024881, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWV+QIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMYy9ob21lL2hhcnNoYWQvYW5hY29uZGEzL2VudnMvcHl0b3JjaC9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4JDAgQBlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMYy9ob21lL2hhcnNoYWQvYW5hY29uZGEzL2VudnMvcHl0b3JjaC9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/M6kqMFUyYYWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="}, "_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": 310, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-6.1.10-060110-generic-x86_64-with-glibc2.36 # 202302060840 SMP PREEMPT_DYNAMIC Mon Feb 6 09:32:56 UTC 2023", "Python": "3.10.9", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1", "GPU Enabled": "True", "Numpy": "1.23.5", "Gym": "0.21.0"}}
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 240.36700435618098, "std_reward": 37.93602574898504, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-12T20:29:32.077646"}
|