Nicolas852
commited on
Commit
•
d78c420
1
Parent(s):
b52942a
best trial of a Lunalander model
Browse files- README.md +37 -0
- best_ppo-LunarLander-v2.zip +3 -0
- best_ppo-LunarLander-v2/_stable_baselines3_version +1 -0
- best_ppo-LunarLander-v2/data +99 -0
- best_ppo-LunarLander-v2/policy.optimizer.pth +3 -0
- best_ppo-LunarLander-v2/policy.pth +3 -0
- best_ppo-LunarLander-v2/pytorch_variables.pth +3 -0
- best_ppo-LunarLander-v2/system_info.txt +8 -0
- config.json +1 -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: 283.20 +/- 17.85
|
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 |
+
```
|
best_ppo-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b7f9650671c4ee9e6f97546c995e9c0989a64b9aeedd2f2d005d2fc43a9d4ed
|
3 |
+
size 147521
|
best_ppo-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
2.0.0a5
|
best_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 0x7f4f50195090>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f4f50195120>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f4f501951b0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f4f50195240>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f4f501952d0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f4f50195360>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f4f501953f0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f4f50195480>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f4f50195510>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f4f501955a0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f4f50195630>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f4f501956c0>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7f4f5018eb80>"
|
21 |
+
},
|
22 |
+
"verbose": 0,
|
23 |
+
"policy_kwargs": {},
|
24 |
+
"num_timesteps": 2015232,
|
25 |
+
"_total_timesteps": 2000000,
|
26 |
+
"_num_timesteps_at_start": 0,
|
27 |
+
"seed": null,
|
28 |
+
"action_noise": null,
|
29 |
+
"start_time": 1706578728523506215,
|
30 |
+
"learning_rate": 0.0014101284211610063,
|
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": -0.007616000000000067,
|
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": 492,
|
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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=",
|
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": 0.9998639676089875,
|
82 |
+
"gae_lambda": 0.972754819571804,
|
83 |
+
"ent_coef": 0.0115628100153596,
|
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:": "gAWVsgIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMTi9ob21lL2hmLy5sb2NhbC9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4RDAgQBlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMTi9ob21lL2hmLy5sb2NhbC9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlGgAjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoH32UfZQoaBZoDYwMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBeMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHP8mZmZmZmZqFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="
|
91 |
+
},
|
92 |
+
"clip_range_vf": null,
|
93 |
+
"normalize_advantage": true,
|
94 |
+
"target_kl": null,
|
95 |
+
"lr_schedule": {
|
96 |
+
":type:": "<class 'function'>",
|
97 |
+
":serialized:": "gAWVsgIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMTi9ob21lL2hmLy5sb2NhbC9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4RDAgQBlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMTi9ob21lL2hmLy5sb2NhbC9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlGgAjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoH32UfZQoaBZoDYwMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBeMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHP1cagdzuVQSFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="
|
98 |
+
}
|
99 |
+
}
|
best_ppo-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf94a2d78175679ebaeaf79f7509e8d34735eae6f4252c75935158a4823cb825
|
3 |
+
size 87978
|
best_ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef8be44d639cb7a041816841811e2dff72c0902977e364299b1597b8ce892abe
|
3 |
+
size 43634
|
best_ppo-LunarLander-v2/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
|
3 |
+
size 864
|
best_ppo-LunarLander-v2/system_info.txt
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: Linux-5.15.133.1-microsoft-standard-WSL2-x86_64-with-glibc2.31 # 1 SMP Thu Oct 5 21:02:42 UTC 2023
|
2 |
+
- Python: 3.10.13
|
3 |
+
- Stable-Baselines3: 2.0.0a5
|
4 |
+
- PyTorch: 2.1.2+cu121
|
5 |
+
- GPU Enabled: False
|
6 |
+
- Numpy: 1.26.3
|
7 |
+
- Cloudpickle: 3.0.0
|
8 |
+
- Gymnasium: 0.28.1
|
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 0x7f4f50195090>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f4f50195120>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f4f501951b0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f4f50195240>", "_build": "<function ActorCriticPolicy._build at 0x7f4f501952d0>", "forward": "<function ActorCriticPolicy.forward at 0x7f4f50195360>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f4f501953f0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f4f50195480>", "_predict": "<function ActorCriticPolicy._predict at 0x7f4f50195510>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f4f501955a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f4f50195630>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f4f501956c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f4f5018eb80>"}, "verbose": 0, "policy_kwargs": {}, "num_timesteps": 2015232, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1706578728523506215, "learning_rate": 0.0014101284211610063, "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": -0.007616000000000067, "_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": 492, "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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 1024, "gamma": 0.9998639676089875, "gae_lambda": 0.972754819571804, "ent_coef": 0.0115628100153596, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "gAWVsgIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMTi9ob21lL2hmLy5sb2NhbC9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4RDAgQBlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMTi9ob21lL2hmLy5sb2NhbC9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlGgAjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoH32UfZQoaBZoDYwMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBeMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHP8mZmZmZmZqFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.133.1-microsoft-standard-WSL2-x86_64-with-glibc2.31 # 1 SMP Thu Oct 5 21:02:42 UTC 2023", "Python": "3.10.13", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.2+cu121", "GPU Enabled": "False", "Numpy": "1.26.3", "Cloudpickle": "3.0.0", "Gymnasium": "0.28.1"}}
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 283.1974506, "std_reward": 17.849028208894055, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-01-30T02:09:17.277790"}
|