EfficientZero

EfficientZero copied to clipboard

I found some BatchNorm(BN) ops are used in config/atari/model.py, but BN is generally not used for RL. So I do some ablations with and without BN. The following results show...

jiaruonan

I wonder if there is any tutorial how to add own custom gym environment to use EffficientZero algorithm ? Where the model is saved after training? How to use saved...

PeterPirog

Hello! Thank you for this open source implementation and your great research! state_norm on this line: https://github.com/YeWR/EfficientZero/blob/main/core/config.py#L57 Do you have any insights into whether normalizing the hidden state helps training...

evanatyourservice

Hey, is there a way to use your implementation with a fixed MDP dataset instead of an environment for 100% offline RL?

tbskrpmnns

./cnode.h:47:42: error: a space is required between consecutive right angle brackets (use '> >') std::vector node_pools;

ipsec

Training is really slow

1

First of all, congratulations on the great work! I've been trying to train an agent to play breakout and the training is really slow. This is really confusing to me...

SergioArnaud

All memory seems on the first GPU

9

Hi, I found something wired when training EfficientZero. I trained the agent on a P40 sever which has 4 24G GPUs and 28 CPUs. But all the computed memory was...

geekyutao

PyTorch Lightning Support

1

Thanks for sharing this codebase, I was wondering if you were planning to support PyTorch Lightning in the future ?

tchaton

Thank you authors for the awesome paper! I have an issue reproducing the results of Breakout. Instead of 414 claimed in the paper, I get 362.43 (average mean performance over...

vladisai

jackfirth