pku-alignment Goto Github PK

.github

alignmentsurvey

AI Alignment: A Comprehensive Survey

beavertails

BeaverTails is a collection of datasets designed to facilitate research on safety alignment in large language models (LLMs).

omnisafe

OmniSafe is an infrastructural framework for accelerating SafeRL research.

proagent

ProAgent: Building Proactive Cooperative Agents with Large Language Models

redman

ReDMan is an open-source simulation platform that provides a standardized implementation of safe RL algorithms for Reliable Dexterous Manipulation.

safe-policy-optimization

NeurIPS 2023: Safe Policy Optimization: A benchmark repository for safe reinforcement learning algorithms

safe-rlhf

Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

safedreamer

ICLR 2024: SafeDreamer: Safe Reinforcement Learning with World Models

safety-gymnasium

NeurIPS 2023: Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark