castawaypirate
commited on
Commit
·
fcdbb70
1
Parent(s):
ef37203
lunar lander v2 ppo model
Browse files- LunarLander-v2-PPO.zip +3 -0
- LunarLander-v2-PPO/_stable_baselines3_version +1 -0
- LunarLander-v2-PPO/data +99 -0
- LunarLander-v2-PPO/policy.optimizer.pth +3 -0
- LunarLander-v2-PPO/policy.pth +3 -0
- LunarLander-v2-PPO/pytorch_variables.pth +3 -0
- LunarLander-v2-PPO/system_info.txt +9 -0
- README.md +37 -0
- config.json +1 -0
- replay.mp4 +0 -0
- results.json +1 -0
LunarLander-v2-PPO.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd36ec0bc70433d1907a84fab635e5e009e59c1edde5159bf38a0bf63b2a1a34
|
3 |
+
size 146191
|
LunarLander-v2-PPO/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
2.0.0a5
|
LunarLander-v2-PPO/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 0x78cb689e2950>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x78cb689e29e0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x78cb689e2a70>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x78cb689e2b00>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x78cb689e2b90>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x78cb689e2c20>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x78cb689e2cb0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x78cb689e2d40>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x78cb689e2dd0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x78cb689e2e60>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x78cb689e2ef0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x78cb689e2f80>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x78cb689db3c0>"
|
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": 1690874690659532702,
|
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": 248,
|
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": 1e-05,
|
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:": "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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:": "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"
|
98 |
+
}
|
99 |
+
}
|
LunarLander-v2-PPO/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:252daa873c47363f2edd1f12988533b9d9515d6e6154e725af62138682fbc94f
|
3 |
+
size 87545
|
LunarLander-v2-PPO/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3fa7e64dada555f7bd8020967ffd20891c0319cf3d3fb25753a09cc6ac4e5c51
|
3 |
+
size 43201
|
LunarLander-v2-PPO/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-PPO/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: False
|
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: 272.59 +/- 16.47
|
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 0x78cb689e2950>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x78cb689e29e0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x78cb689e2a70>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x78cb689e2b00>", "_build": "<function ActorCriticPolicy._build at 0x78cb689e2b90>", "forward": "<function ActorCriticPolicy.forward at 0x78cb689e2c20>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x78cb689e2cb0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x78cb689e2d40>", "_predict": "<function ActorCriticPolicy._predict at 0x78cb689e2dd0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x78cb689e2e60>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x78cb689e2ef0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x78cb689e2f80>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x78cb689db3c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1690874690659532702, "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:": "gAWVGgwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQHEE06o2n8+MAWyUTRMBjAF0lEdAu2MjUx20RnV9lChoBkdAb4TwhnrY5GgHTQ4BaAhHQLtjR1uR9w51fZQoaAZHQHEdm8274BVoB0v3aAhHQLtjoRjSXt11fZQoaAZHQHAQEkWykbhoB00mAWgIR0C7Y7QA2hqTdX2UKGgGR0BxMJCtzS1FaAdL9WgIR0C7ZDTR6WxAdX2UKGgGR0BxhWxJNCZ4aAdNCQFoCEdAu2RGukk8inV9lChoBkdAbjRfw7T2FmgHTQgBaAhHQLtkYBBRhtt1fZQoaAZHQHDcT8LrontoB0vraAhHQLtkwVrAP/d1fZQoaAZHQG2aCYTj/+9oB00dAWgIR0C7ZM4ISlFddX2UKGgGR0BxxfEIgNgCaAdNdQFoCEdAu2UV2+wkgXV9lChoBkdAb92sGPgeimgHS/toCEdAu2UXSb6P83V9lChoBkdAbr7uO0b962gHS/loCEdAu2VG+XZ5A3V9lChoBkdAcQ7UJfICEGgHS+loCEdAu2Vw70WdmXV9lChoBkdAcDvDjin5z2gHS+toCEdAu2WbeXRgJHV9lChoBkdAbzsBOpKjBWgHS/5oCEdAu2X/E/B3zXV9lChoBkdAcE9Riw0O3GgHTR0BaAhHQLtmD4agmJF1fZQoaAZHQHGqHko4MnZoB0v0aAhHQLtmSJFLFn91fZQoaAZHQHA6iM98qnZoB00LAWgIR0C7ZpdAgPmQdX2UKGgGR0BuHG/FirksaAdNVgFoCEdAu2bOeqaPS3V9lChoBkdAcWY7kXDWLGgHS91oCEdAu2clZSvTw3V9lChoBkdAbVnM2WIGhWgHTR0BaAhHQLtnYXC0ngJ1fZQoaAZHQHG+0Dp1RtRoB00WAWgIR0C7Z2YptrKvdX2UKGgGR0BxGK/i5uqFaAdNNQFoCEdAu2eb2zv7WXV9lChoBkdAblomnfl6q2gHS/ZoCEdAu2fIPTXrdHV9lChoBkdAZ5xG6wt8NWgHTV0CaAhHQLtoKH+6y0N1fZQoaAZHQG0FdORDCxhoB0v6aAhHQLtoOUypJf91fZQoaAZHQFTuzyBkI5ZoB0vGaAhHQLtoSmlZX+51fZQoaAZHQHAdpeE7GNtoB00PAWgIR0C7aErq6e5GdX2UKGgGR0BzVsQrc0tRaAdNSgFoCEdAu2h+rksBhnV9lChoBkdAcO9J66asqGgHTTMBaAhHQLtolKneizt1fZQoaAZHQG/xhWxQizNoB0vjaAhHQLtoo6zVtoB1fZQoaAZHQHCf5Cv5gw5oB00OAWgIR0C7aL3CKrJbdX2UKGgGR0Btgt1SwW30aAdL92gIR0C7aTuzyBkJdX2UKGgGR0BwGtEsrd30aAdL7WgIR0C7aby0jTrndX2UKGgGR0Bw3CpwS8J2aAdNFgFoCEdAu2oOWu5jIHV9lChoBkdAciqB4D9wWGgHTRkBaAhHQLtq0yP+4sp1fZQoaAZHQDIqRaHKwINoB0vEaAhHQLtq/Vgx8D11fZQoaAZHQHB5JGOMl1NoB00QAWgIR0C7awjfek57dX2UKGgGR0Bve767/XGwaAdNAAFoCEdAu2sTwVj7RHV9lChoBkdAcmIoFmnO0WgHTSgBaAhHQLtrbgte2NN1fZQoaAZHQHNdhGx2SuBoB0vhaAhHQLtrgTj/+851fZQoaAZHQG2Kh3Roh6loB0vzaAhHQLtrzsMRYih1fZQoaAZHQHFaMXJo0yhoB00BAWgIR0C7a9bjPv8ZdX2UKGgGR0BwDEQcxTKlaAdNIgFoCEdAu2vcE7nxKHV9lChoBkdAb7arhBJI2GgHS/ZoCEdAu3IBe5WilHV9lChoBkdAceXcebNKRWgHTRQBaAhHQLtyH0zTF2p1fZQoaAZHQHKYZnlGPPtoB00PAWgIR0C7ch5NoJzDdX2UKGgGR0Bx8bErGza9aAdL62gIR0C7ckRJqZc+dX2UKGgGR0BuxTMxGlQ/aAdNAwFoCEdAu3LavwEyL3V9lChoBkdAMRCxFAmiQGgHS9FoCEdAu3MZuR9w33V9lChoBkdAcbaIDoyKvWgHTTUBaAhHQLtzsWAf+0h1fZQoaAZHQG/bzguRLbpoB00NAWgIR0C7c//cer+6dX2UKGgGR0BwNvWXkYGdaAdL+mgIR0C7dBmgWac7dX2UKGgGR0BvgLg88s+WaAdNGAFoCEdAu3Qfehwl0HV9lChoBkdAbvzRE4Nqg2gHTRoBaAhHQLt0NzPKMeh1fZQoaAZHQG5J5NwiqyZoB00AAWgIR0C7dD6ews5GdX2UKGgGR0BwXTA8B+4LaAdL+2gIR0C7dGv7el9CdX2UKGgGR0Bw/YecQRPHaAdNEwFoCEdAu3SijtXxOXV9lChoBkdAbiwfFJg9eWgHTSQBaAhHQLt02Qw9JSR1fZQoaAZHQHAH6dtl7MRoB0voaAhHQLt02OVxCIF1fZQoaAZHQG2mX6InBtVoB00SAWgIR0C7dRx0MgEEdX2UKGgGR0BKUsxO+IuXaAdLr2gIR0C7dSRXwLE2dX2UKGgGR0BvtQzWPLgXaAdNIAFoCEdAu3VCMhouf3V9lChoBkdAcNtK77Kq42gHTQkBaAhHQLt10dYGMXJ1fZQoaAZHQHGlSOaOPvNoB0voaAhHQLt22Fy7wrl1fZQoaAZHQEDq/20zCUJoB0vXaAhHQLt22IjGDL91fZQoaAZHQHFM801qFh5oB0vxaAhHQLt274+r2g51fZQoaAZHQHC2p2U0Nz9oB00BAWgIR0C7dwUfDDTCdX2UKGgGR0BuWf8uSOinaAdNGAFoCEdAu3c9jUd7wHV9lChoBkdAcREUHIIWxmgHTTMBaAhHQLt3SMDfWMF1fZQoaAZHQHE/tJOFg2JoB00hAWgIR0C7d3cw+MZQdX2UKGgGR0BuSEg8r7O3aAdL7GgIR0C7d6GmUGFBdX2UKGgGR0Bw/aIP9UCJaAdNDAFoCEdAu3fEG9pRGnV9lChoBkdActbWN3np0WgHS99oCEdAu3fJg6U7jnV9lChoBkdAcRYBAOavzWgHS/xoCEdAu3gXS1E3KnV9lChoBkdAcdWkOqebu2gHTQIBaAhHQLt4TtFa0Qd1fZQoaAZHQHFi/NmlImRoB00zAWgIR0C7eGuMZP2xdX2UKGgGR0BwPmmBOHnEaAdL9WgIR0C7eMX49HMEdX2UKGgGR0BQaFiSaEzwaAdLwmgIR0C7eeLulXRxdX2UKGgGR0BvGwMH8jzJaAdL+mgIR0C7eggxi5NHdX2UKGgGR0BxT8JTl1bJaAdL82gIR0C7enJuqFRHdX2UKGgGR0BvBhIczZYgaAdNHAFoCEdAu3qoQnQY13V9lChoBkdAcYnU0Nz8xmgHTQ4BaAhHQLt6pm+Cbtt1fZQoaAZHQHJJu6VdHDtoB00YAWgIR0C7erFIEr5JdX2UKGgGR0A84yoGY8dQaAdN6ANoCEdAu3sPAWSEDnV9lChoBkdAbOoWqtHQQmgHS/NoCEdAu3sn7UG3WnV9lChoBkdAcBB20iQkomgHTR4BaAhHQLt7LLofSx91fZQoaAZHQHKl+8Gs3hpoB00QAWgIR0C7e1sa0hNedX2UKGgGR0BtJcvTPSlWaAdNGgFoCEdAu3uyGCZnc3V9lChoBkdAcMhhHbypaWgHTQoBaAhHQLt74c9GI9F1fZQoaAZHQG3h/95yEL9oB0vsaAhHQLt74IvJzT51fZQoaAZHQHDakWl/H5toB0voaAhHQLt8QfwZwXJ1fZQoaAZHQHJ7BrrPdEdoB00jAWgIR0C7fIECmuTzdX2UKGgGR0ByIvsXzlLfaAdL2GgIR0C7fULXpW3jdX2UKGgGR0BPAcM3IdU9aAdLv2gIR0C7fWipWFN+dX2UKGgGR0BxRNyS3b22aAdNFQFoCEdAu34hxXGOuXV9lChoBkdAcW0QzUI9kmgHTQEBaAhHQLt+VDiwSrZ1fZQoaAZHQG9o3cQAdXFoB0vwaAhHQLt+sCZF5Od1fZQoaAZHQHAFkb1h9b5oB00OAWgIR0C7fsEH2RJVdX2UKGgGR0Bv/f3UQTVUaAdNCwFoCEdAu37A7p3X7XVlLg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 248, "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": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 1e-05, "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": "False", "Numpy": "1.22.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
replay.mp4
ADDED
Binary file (173 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 272.59006429999994, "std_reward": 16.467039574277205, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-08-01T08:13:52.145593"}
|