PyTorch implementation of Soft-Actor-Critic and Prioritized Experience Replay (PER) + Emphasizing Recent Experience (ERE) + Munchausen RL + D2RL and parallel Environments.

DSAC-v2; DSAC-T; DASC; Distributional Soft Actor-Critic

[ICRA 2023] Intention Aware Robot Crowd Navigation with Attention-Based Interaction Graph

This repository contains the source code for our paper: "NaviSTAR: Socially Aware Robot Navigation with Hybrid Spatio-Temporal Graph Transformer and Preference Learning". For more details, please r…

Guiding Like a Toddler: From Sparse to Dense Rewards Transition in Goal-Oriented Reinforcement Learning