Chongjie Zhang

19

Papers

8

Total Citations

Papers (19)

Learning to Plan Before Answering: Self-Teaching LLMs to Learn Abstract Plans for Problem Solving

Enhancing Decision-Making of Large Language Models via Actor-Critic

Planning, Fast and Slow: Online Reinforcement Learning with Action-Free Offline Data via Multiscale Planners

Bayesian Design Principles for Offline-to-Online Reinforcement Learning

Bridging Imagination and Reality for Model-Based Deep Reinforcement Learning

NeurIPS 2020arXiv

Episodic Multi-agent Reinforcement Learning with Curiosity-driven Exploration

NeurIPS 2021arXiv

Celebrating Diversity in Shared Multi-Agent Reinforcement Learning

NeurIPS 2021arXiv

Model-Based Reinforcement Learning via Imagination with Derived Memory

On the Estimation Bias in Double Q-Learning

NeurIPS 2021arXiv

Towards Understanding Cooperative Multi-Agent Q-Learning with Value Factorization

NeurIPS 2021arXiv

Offline Reinforcement Learning with Reverse Model-based Imagination

NeurIPS 2021arXiv

Low-Rank Modular Reinforcement Learning via Muscle Synergy

NeurIPS 2022arXiv

RORL: Robust Offline Reinforcement Learning via Conservative Smoothing

NeurIPS 2022arXiv

Non-Linear Coordination Graphs

NeurIPS 2022arXiv

CUP: Critic-Guided Policy Reuse

NeurIPS 2022arXiv

Safe Opponent-Exploitation Subgame Refinement

LAPO: Latent-Variable Advantage-Weighted Policy Optimization for Offline Reinforcement Learning

Unsupervised Behavior Extraction via Random Intent Priors

NeurIPS 2023arXiv

Conservative Offline Policy Adaptation in Multi-Agent Games