EfficientZero VS RHO-Loss

Here's an algorithm that is more sample efficient : https://github.com/YeWR/EfficientZero

Use multiprocessing to have more GPU workers could help. My code based on EfficientZero https://github.com/YeWR/EfficientZero is utilizing CPUs and GPUs to 90%. It uses Ray for multiprocessing and splits Reanalyze into CPU and GPU workers to maximize resource utilization. By the way, it's not converging to optimal policy well: it gets stuck at 50% optimal episode return at with a small amount of training. Have you had this issue before?

Found relevant code at https://github.com/YeWR/EfficientZero + all code implementations here

Mastering Atari Games with Limited Data – EfficientZero ( Human sample -efficiency! ) Paper: https://arxiv.org/abs/2111.00210 Lesswrong article about the paper: https://www.lesswrong.com/posts/mRwJce3npmzbKfxws/efficientzero-how-it-works Github: https://github.com/YeWR/EfficientZero

Have you seen https://github.com/YeWR/EfficientZero EfficientZero yet? This agent is able to solve problems with unknown rules, where the agent starts only with information about the shape of the inputs and reward feedback. With superhuman ability - it needs less training data than humans do - and SoTA trumping results on the problems it has been tried on. (various atari/Go/chess/etc)

Open-source codebase for EfficientZero - am I missing something or the repo is empty?

Code: https://github.com/YeWR/EfficientZero

Code for https://arxiv.org/abs/2111.00210 found: https://github.com/YeWR/EfficientZero

RHO-LOSS - Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt - Trains Models 18x faster with higher accuracy Paper: https://arxiv.org/abs/2206.07137 Github: https://github.com/OATML/RHO-Loss