xiezhipeng-git

character Input does not take effect

2

After the update, the role control using inputsystem does not take effect Version a319c0da6c6a55baadc31c10c8120a28e959766b [a319c0d] Need add UNITY_INPUT_SYSTEM_EXISTS in playersetting

tutorial_BipedalWalker_v3.ipynb 跑不通

3

直接运行tutorial_BipedalWalker_v3.ipynb 报错 --------------------------------------------------------------------------- AttributeError Traceback (most recent call last) e:\study\machineStudy\project\matd3\ElegantRL\tutorial_BipedalWalker_v3.ipynb Cell 15 in () ----> [1](vscode-notebook-cell:/e%3A/study/machineStudy/project/matd3/ElegantRL/tutorial_BipedalWalker_v3.ipynb#X20sZmlsZQ%3D%3D?line=0) train_and_evaluate(args) File e:\study\machineStudy\project\matd3\ElegantRL\elegantrl\train\run.py:91, in train_and_evaluate(args) 88 buffer = init_buffer(args, gpu_id) 89 evaluator = init_evaluator(args,...

[BUG]: lamb Learning in the opposite direction by big learn rate

8

### 🐛 Describe the bug BUg：lamb Learning in the opposite direction. Reproduce:git clone https://github.com/Lizhi-sjtu/MARL-code-pytorch in MADDPG_MATD3_main.py use simple_spread discrete False change: parser.add_argument("--lr_a", type=float, default=1e-2, help="Learning rate of actor 5e-4") parser.add_argument("--lr_c",...

会考虑支持集群训练吗?像Acme,seed_rl

1

seed_rl让神经网络训练提升几十几百倍速度。如果支持的话。那么这个框架就有了能够落实各种大型项目的意义了

chatGpt训练算法从transformer变成ppo以后。可以看到ai的效果和gpt3有了本质的提升。而强化学习中ppo算法还有很多提升空间。也还有不同的强化算法也有提升空间td3,deepnash。那么如果使用这些算法，并且加上集群的功能。那还了得。easyNLP可以自定义算法吗？怎么定义？又支持集群训练吗？怎么处理？以及能支持单机训练百亿参数的原理是蒸馏吗？

os：win11 wsl2 vscode version:trailtets 5.9.0 In vscode bugs Info:https://github.com/zeromq/pyzmq/issues/1855 https://github.com/microsoft/vscode-jupyter/issues/8630

I found agent def sync_out(self, device="cpu") use cpu.then I try change to gpu.then I change code def sync_out(self, device="cpu"): device = self.device or device = self.device.type 1.but it has error...

**Describe the bug** Unavailable moduels ['mlagent', 'mujoco', 'nes', 'procgen'] module: mlagent error: Traceback (most recent call last): File "e:\study\machineStudy\project\Jorldy\JORLDY\jorldy\core\env\__init__.py", line 21, in module = __import__(module_path, fromlist=[None]) File "e:\study\machineStudy\project\Jorldy\JORLDY\jorldy\core\env\mlagent.py", line 1,...

we need maRL