Upload PPO_LLV2_1024_64_32_500K
Browse files- PPO_LLV2_1024_64_32_500K.zip +3 -0
- PPO_LLV2_1024_64_32_500K/_stable_baselines3_version +1 -0
- PPO_LLV2_1024_64_32_500K/data +99 -0
- PPO_LLV2_1024_64_32_500K/policy.optimizer.pth +3 -0
- PPO_LLV2_1024_64_32_500K/policy.pth +3 -0
- PPO_LLV2_1024_64_32_500K/pytorch_variables.pth +3 -0
- PPO_LLV2_1024_64_32_500K/system_info.txt +8 -0
- README.md +37 -0
- config.json +1 -0
- replay.mp4 +0 -0
- results.json +1 -0
PPO_LLV2_1024_64_32_500K.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4cf043726dc2d1a85128643d5cf1ae3192d4f037610ff13724902fb27198451
|
3 |
+
size 149017
|
PPO_LLV2_1024_64_32_500K/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
2.0.0a5
|
PPO_LLV2_1024_64_32_500K/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 0x7ff27b5ddda0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff27b5dde40>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff27b5ddee0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff27b5ddf80>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7ff27b5de020>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7ff27b5de0c0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7ff27b5de160>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff27b5de200>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7ff27b5de2a0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff27b5de340>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff27b5de3e0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff27b5de480>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7ff27b5da000>"
|
21 |
+
},
|
22 |
+
"verbose": 2,
|
23 |
+
"policy_kwargs": {},
|
24 |
+
"num_timesteps": 524288,
|
25 |
+
"_total_timesteps": 500000,
|
26 |
+
"_num_timesteps_at_start": 0,
|
27 |
+
"seed": null,
|
28 |
+
"action_noise": null,
|
29 |
+
"start_time": 1712580237497407178,
|
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:": "gAWVkwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksghZSMAUOUdJRSlC4="
|
39 |
+
},
|
40 |
+
"_last_original_obs": null,
|
41 |
+
"_episode_num": 0,
|
42 |
+
"use_sde": false,
|
43 |
+
"sde_sample_freq": -1,
|
44 |
+
"_current_progress_remaining": -0.04857599999999995,
|
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": 64,
|
55 |
+
"n_steps": 1024,
|
56 |
+
"gamma": 0.999,
|
57 |
+
"gae_lambda": 0.98,
|
58 |
+
"ent_coef": 0.01,
|
59 |
+
"vf_coef": 0.5,
|
60 |
+
"max_grad_norm": 0.5,
|
61 |
+
"batch_size": 64,
|
62 |
+
"n_epochs": 4,
|
63 |
+
"clip_range": {
|
64 |
+
":type:": "<class 'function'>",
|
65 |
+
":serialized:": "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"
|
66 |
+
},
|
67 |
+
"clip_range_vf": null,
|
68 |
+
"normalize_advantage": true,
|
69 |
+
"target_kl": null,
|
70 |
+
"observation_space": {
|
71 |
+
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
72 |
+
":serialized:": "gAWVdgIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoCIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoESiWCAAAAAAAAAABAQEBAQEBAZRoFUsIhZRoGXSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBEoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaAtLCIWUaBl0lFKUjARoaWdolGgRKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgLSwiFlGgZdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=",
|
73 |
+
"dtype": "float32",
|
74 |
+
"bounded_below": "[ True True True True True True True True]",
|
75 |
+
"bounded_above": "[ True True True True True True True True]",
|
76 |
+
"_shape": [
|
77 |
+
8
|
78 |
+
],
|
79 |
+
"low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]",
|
80 |
+
"high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
|
81 |
+
"low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]",
|
82 |
+
"high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
|
83 |
+
"_np_random": null
|
84 |
+
},
|
85 |
+
"action_space": {
|
86 |
+
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
87 |
+
":serialized:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
88 |
+
"n": "4",
|
89 |
+
"start": "0",
|
90 |
+
"_shape": [],
|
91 |
+
"dtype": "int64",
|
92 |
+
"_np_random": null
|
93 |
+
},
|
94 |
+
"n_envs": 32,
|
95 |
+
"lr_schedule": {
|
96 |
+
":type:": "<class 'function'>",
|
97 |
+
":serialized:": "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"
|
98 |
+
}
|
99 |
+
}
|
PPO_LLV2_1024_64_32_500K/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d345e1ff8f3bd0a04fab008ad0055f3b7f87eabb02900b5db115f5513677a69e
|
3 |
+
size 88490
|
PPO_LLV2_1024_64_32_500K/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef6e57b8f0852f2955e143c11cd77db16ceda11416d547751c75a778f7b05a10
|
3 |
+
size 43762
|
PPO_LLV2_1024_64_32_500K/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
|
3 |
+
size 864
|
PPO_LLV2_1024_64_32_500K/system_info.txt
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: Linux-5.15.146.1-microsoft-standard-WSL2-x86_64-with-glibc2.35 # 1 SMP Thu Jan 11 04:09:03 UTC 2024
|
2 |
+
- Python: 3.11.8
|
3 |
+
- Stable-Baselines3: 2.0.0a5
|
4 |
+
- PyTorch: 2.2.2+cu121
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.26.4
|
7 |
+
- Cloudpickle: 3.0.0
|
8 |
+
- Gymnasium: 0.28.1
|
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: 192.50 +/- 73.22
|
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 0x7ff27b5ddda0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff27b5dde40>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff27b5ddee0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff27b5ddf80>", "_build": "<function ActorCriticPolicy._build at 0x7ff27b5de020>", "forward": "<function ActorCriticPolicy.forward at 0x7ff27b5de0c0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ff27b5de160>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff27b5de200>", "_predict": "<function ActorCriticPolicy._predict at 0x7ff27b5de2a0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff27b5de340>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff27b5de3e0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff27b5de480>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7ff27b5da000>"}, "verbose": 2, "policy_kwargs": {}, "num_timesteps": 524288, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1712580237497407178, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQQAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYABAAAAAAAAID0Zj2upaG6kE8zu3uSdbwKWYQ6prBWvQAAAAAAAIA/gFOXvXw3pT53UAi+FWCqvu/zHb71ZVC9AAAAAAAAAAAAiG07HxXNueh8CD7lBIE2X1MTO1/2gTUAAIA/AACAPyaR2D6BAYo/UXO3Pkfmv77ne8I+5E2YPQAAAAAAAAAAs9+4PeFQi7qbO3k8fyGYvZtv1blmqTW9AAAAAAAAAABmZvY4uG61P4IbGjzzR489Da/LumN1+LwAAAAAAAAAAAqrgD4kxVI8AOLmu//NjbohD8Y9Dmb/OgAAgD8AAAAAFvtmvnYEB7zOTq07RU0YOZ1HUj0yAf65AACAPwAAgD8Nuza+uDD4OjZZFbwblU45TP+7vKa+GLoAAIA/AACAP0Cu5L1cMzm6AiTNvG+ZwLi/gk25zbouOAAAgD8AAIA/0xwCvj1ULbsOH5w6kG++ObBQMzzzy4i5AACAPwAAgD8zEOA8KfBKusIQEDvDlkm25TaPu/SdQ7UAAIA/AACAP+aiNz1IV4G69cHtuaxiArWzpd66cBgKOQAAgD8AAIA/MwPiusO9a7oo72k77xHhN0KygLvrWaE2AACAPwAAgD/WPoo+9C0JvQDifz7TglM7b257vhr+hb0AAAAAAACAP838Tb3hzIq6ZSR5O13CMzMHwlS7E+9CMwAAgD8AAIA/M0vdPY+GPrrHf4E8uauRPM3YjrkOOfU8AACAPwAAgD9DsQU/XZrevdMWFDzjJ6M8JOsZvgUa47oAAIA/AACAP/On3j0UKte6I2fkO5XvYzyddjG8kLBIPQAAgD8AAIA/5mFTPaQAULku8Aq8cNiqNxoroDpbvxq3AACAPwAAgD+a65I9MSI5PiMsEj1Wr3m+09ZsvhvAWT0AAAAAAAAAAI0xmL0I3wc/7iX3vU77tb5Dxca8nhnKvAAAAAAAAAAAWkbOvVRKjz8G3G++s9PmviMxqb1p/qY8AAAAAAAAAADTQ3Q+SIroO7WmLb22gJC64nSAPU5khbsAAIA/AACAP7Vrqr4BHK+8uDBkPAtbbjyE2MA9e8L1vAAAAAAAAAAAMwjGva5/oLpLa6y4x0TpvLwHfjuS8cs9AACAPwAAAADNNi08FDaMuqqCazyf2BW52J2fu8XeELgAAIA/AACAPw0dxz0gf+M+7lJTvWXZpr5ljBI+m8NuuwAAAAAAAAAAzYSXPY82QLq+vQY6dzNGNG0Mt7pNxBy5AACAPwAAgD/uvqO+VGqZvAvLFrwbD1K89zrSPdK2gb0AAAAAAAAAAJqg27yKuLo/5i9uvhmRcj1uY6I8FjSDvAAAAAAAAAAAWqGrvT3CBLuDJtw7PAHDPKHtCLxR3ac9AACAPwAAgD+UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSyBLCIaUjAFDlHSUUpQu"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVkwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksghZSMAUOUdJRSlC4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.04857599999999995, "_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": 64, "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, "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:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 32, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.146.1-microsoft-standard-WSL2-x86_64-with-glibc2.35 # 1 SMP Thu Jan 11 04:09:03 UTC 2024", "Python": "3.11.8", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.2.2+cu121", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "3.0.0", "Gymnasium": "0.28.1"}}
|
replay.mp4
ADDED
Binary file (190 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 192.5007762, "std_reward": 73.21535091987441, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-08T15:01:42.478535"}
|