HunterLanier
commited on
Commit
·
b4a70b0
1
Parent(s):
30ce037
Upload PPO trained agent
Browse files- Lunar_Lander_PPO_v1.zip +3 -0
- Lunar_Lander_PPO_v1/_stable_baselines3_version +1 -0
- Lunar_Lander_PPO_v1/data +99 -0
- Lunar_Lander_PPO_v1/policy.optimizer.pth +3 -0
- Lunar_Lander_PPO_v1/policy.pth +3 -0
- Lunar_Lander_PPO_v1/pytorch_variables.pth +3 -0
- Lunar_Lander_PPO_v1/system_info.txt +9 -0
- README.md +37 -0
- config.json +1 -0
- replay.mp4 +0 -0
- results.json +1 -0
Lunar_Lander_PPO_v1.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d05c1d9dc24278be8fc139324e14a312be14ad769faad66b96524e6b6898845
|
3 |
+
size 146757
|
Lunar_Lander_PPO_v1/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
2.0.0a5
|
Lunar_Lander_PPO_v1/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 0x7b9f2641cb80>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b9f2641cc10>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b9f2641cca0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b9f2641cd30>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7b9f2641cdc0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7b9f2641ce50>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7b9f2641cee0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b9f2641cf70>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7b9f2641d000>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b9f2641d090>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b9f2641d120>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7b9f2641d1b0>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7b9f26414c40>"
|
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": 1690056501636830579,
|
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": 254,
|
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": 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": 64,
|
87 |
+
"n_epochs": 4,
|
88 |
+
"clip_range": {
|
89 |
+
":type:": "<class 'function'>",
|
90 |
+
":serialized:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
|
91 |
+
},
|
92 |
+
"clip_range_vf": null,
|
93 |
+
"normalize_advantage": true,
|
94 |
+
"target_kl": null,
|
95 |
+
"lr_schedule": {
|
96 |
+
":type:": "<class 'function'>",
|
97 |
+
":serialized:": "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"
|
98 |
+
}
|
99 |
+
}
|
Lunar_Lander_PPO_v1/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48c52ee947dce75cc46642a5c71881544e1c9cc7070b42507a026bbf7bbbf530
|
3 |
+
size 87929
|
Lunar_Lander_PPO_v1/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc3bf6a63cbb8c35a7e397b36b1b3eff7be0f8d27c278af3664f9a51588a98d8
|
3 |
+
size 43329
|
Lunar_Lander_PPO_v1/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
|
3 |
+
size 431
|
Lunar_Lander_PPO_v1/system_info.txt
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: Linux-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 UTC 2023
|
2 |
+
- Python: 3.10.6
|
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
|
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: 253.01 +/- 13.61
|
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 0x7b9f2641cb80>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b9f2641cc10>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b9f2641cca0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b9f2641cd30>", "_build": "<function ActorCriticPolicy._build at 0x7b9f2641cdc0>", "forward": "<function ActorCriticPolicy.forward at 0x7b9f2641ce50>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7b9f2641cee0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b9f2641cf70>", "_predict": "<function ActorCriticPolicy._predict at 0x7b9f2641d000>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b9f2641d090>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b9f2641d120>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7b9f2641d1b0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7b9f26414c40>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1690056501636830579, "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": 254, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "gAWVcAIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoECiWCAAAAAAAAAABAQEBAQEBAZRoFEsIhZRoGHSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBAoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaApLCIWUaBh0lFKUjARoaWdolGgQKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgKSwiFlGgYdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=", "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": 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, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 UTC 2023", "Python": "3.10.6", "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"}}
|
replay.mp4
ADDED
Binary file (202 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 253.0106153, "std_reward": 13.607263560117259, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-22T20:34:08.231352"}
|