reward-shaping
Implementation of Humanoid Standing Up, from the paper "Learning Humanoid Standing-up Control across Diverse Postures" out of Shanghai, in Pytorch
Inference-time scaling for LLMs-as-a-judge.
Catch reward traps before training. Static analysis for RL reward functions.
A gymnasium-compatible framework to create reinforcement learning (RL) environment for solving the optimal power flow (OPF) problem. Contains five OPF benchmark environments for comparable research.
Reward shaping library
