Official Implementation for the paper "SR-AIF: Solving Sparse-Reward Robotic Tasks from Pixels with Active Inference and World Models"

Official PyTorch Implementation for Metric Residual Networks for Sample Efficient Goal-Conditioned Reinforcement Learning

Sparse environment for MuJoCo suite (v2 and v3)

This repo empirically investigates that Weight Agnostic Neural Networks (WANN) are a promising alternative to traditional RL models in sparse settings.