taehoon1lee
commited on
Commit
·
9195115
1
Parent(s):
edaeed8
first commit
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 +99 -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 +9 -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: 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: 276.24 +/- 15.48
|
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 0x7f5b0e512710>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f5b0e5127a0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f5b0e512830>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f5b0e5128c0>", "_build": "<function ActorCriticPolicy._build at 0x7f5b0e512950>", "forward": "<function ActorCriticPolicy.forward at 0x7f5b0e5129e0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f5b0e512a70>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f5b0e512b00>", "_predict": "<function ActorCriticPolicy._predict at 0x7f5b0e512b90>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f5b0e512c20>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f5b0e512cb0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f5b0e512d40>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f5b0e5078c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1688133702237699881, "learning_rate": 0.0003, "tensorboard_log": null, "_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, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 380, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True True True True True True]", "bounded_above": "[ True True True True True True True True]", "_shape": [8], "low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "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:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
ppo-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7a4f56c02632bece12355b4a7cb779f347d416d52a399c16058388ee1b990bf
|
3 |
+
size 146638
|
ppo-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
2.0.0a5
|
ppo-LunarLander-v2/data
ADDED
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 0x7f5b0e512710>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f5b0e5127a0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f5b0e512830>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f5b0e5128c0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f5b0e512950>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f5b0e5129e0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f5b0e512a70>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f5b0e512b00>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f5b0e512b90>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f5b0e512c20>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f5b0e512cb0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f5b0e512d40>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7f5b0e5078c0>"
|
21 |
+
},
|
22 |
+
"verbose": 1,
|
23 |
+
"policy_kwargs": {},
|
24 |
+
"num_timesteps": 1015808,
|
25 |
+
"_total_timesteps": 1000000,
|
26 |
+
"_num_timesteps_at_start": 0,
|
27 |
+
"seed": null,
|
28 |
+
"action_noise": null,
|
29 |
+
"start_time": 1688133702237699881,
|
30 |
+
"learning_rate": 0.0003,
|
31 |
+
"tensorboard_log": null,
|
32 |
+
"_last_obs": {
|
33 |
+
":type:": "<class 'numpy.ndarray'>",
|
34 |
+
":serialized:": "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"
|
35 |
+
},
|
36 |
+
"_last_episode_starts": {
|
37 |
+
":type:": "<class 'numpy.ndarray'>",
|
38 |
+
":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
39 |
+
},
|
40 |
+
"_last_original_obs": null,
|
41 |
+
"_episode_num": 0,
|
42 |
+
"use_sde": false,
|
43 |
+
"sde_sample_freq": -1,
|
44 |
+
"_current_progress_remaining": -0.015808000000000044,
|
45 |
+
"_stats_window_size": 100,
|
46 |
+
"ep_info_buffer": {
|
47 |
+
":type:": "<class 'collections.deque'>",
|
48 |
+
":serialized:": "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"
|
49 |
+
},
|
50 |
+
"ep_success_buffer": {
|
51 |
+
":type:": "<class 'collections.deque'>",
|
52 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
+
},
|
54 |
+
"_n_updates": 380,
|
55 |
+
"observation_space": {
|
56 |
+
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
+
":serialized:": "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",
|
58 |
+
"dtype": "float32",
|
59 |
+
"bounded_below": "[ True True True True True True True True]",
|
60 |
+
"bounded_above": "[ True True True True True True True True]",
|
61 |
+
"_shape": [
|
62 |
+
8
|
63 |
+
],
|
64 |
+
"low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]",
|
65 |
+
"high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
|
66 |
+
"low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]",
|
67 |
+
"high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
|
68 |
+
"_np_random": null
|
69 |
+
},
|
70 |
+
"action_space": {
|
71 |
+
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
72 |
+
":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=",
|
73 |
+
"n": "4",
|
74 |
+
"start": "0",
|
75 |
+
"_shape": [],
|
76 |
+
"dtype": "int64",
|
77 |
+
"_np_random": null
|
78 |
+
},
|
79 |
+
"n_envs": 16,
|
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 |
+
"lr_schedule": {
|
96 |
+
":type:": "<class 'function'>",
|
97 |
+
":serialized:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
|
98 |
+
}
|
99 |
+
}
|
ppo-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:088f5e0d370e932363d7ee396dd0fc31badf947163f02489366bd2001076a24e
|
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:d537b2e7a3add052348dcb957aacfa8ff95db09d123122bb7b3e02f592bdf409
|
3 |
+
size 43329
|
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 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: Linux-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023
|
2 |
+
- Python: 3.10.12
|
3 |
+
- Stable-Baselines3: 2.0.0a5
|
4 |
+
- PyTorch: 2.0.1+cu118
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.22.4
|
7 |
+
- Cloudpickle: 2.2.1
|
8 |
+
- Gymnasium: 0.28.1
|
9 |
+
- OpenAI Gym: 0.25.2
|
replay.mp4
ADDED
Binary file (119 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 276.2395533, "std_reward": 15.483419256034384, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-06-30T14:35:21.731791"}
|