Harshit Sikchi

safeRL. Safe Reinforcement Learning algorithms

awesome-ai-safety. A curated list of awesome AI safety papers, projects and communities.

AWAC. Advantage weighted Actor Critic for Offline RL

LOOP. Learning Off-Policy with Online Planning [CoRL 2021 Best Paper Finalist]

offline_rl. Pytorch implementation of state-of-the-art offline reinforcement learning algorithms.

pytorch_CPO. Simple implementation for Constrained Policy Optimization in Pytorch

DVL. A Dual-RL method DVL: Dual-V Learning for offline and online reinforcement learning

BoxYolo. 3D-object detection using RGBD images

LBPO. Lyapunov Barrier Policy Optimization - Simple Pytorch implementation for Model free Safe Reinforcement Learning

rank-game. SOTA algorithms for imitation learning (LfD and LfO) - Ranking algorithms for imitation learning (TMLR 2023)

gym-gazebo. A toolkit for developing and comparing reinforcement learning algorithms using ROS and Gazebo.

SMORe. Official repository for Paper " Score Models for Offline Goal-Conditioned Reinforcement Learning" (ICLR 2024)

DILO. Authors implementation of DILO: Dual Imitation from Observation presented at CoRL 2024

TD3_from_demonstration. Using expert demonstrations in TD3 to learn faster

spinningup. Python

DepthSegnet. Depth fused in a encoder-decoder architecture

long_horizon_manipulation. Python

ReCOIL. Python

Object-Detection. Various methods and evolution of Object detection methods

capella. Python

baby_quic. Miniature implementation of Google's QUIC protocol

RGBD-Vision. Navigation using Algorithms for Stereo Vision