I have worked on AI agents in game environments, spanning text adventure games and visually rich video games. These projects explore reinforcement learning, planning, reasoning, exploration, generalization, morality, and safe decision making.
🗺️ Text Adventure Games
Research on language-based game agents, from deep reinforcement learning and generalization to moral decision making, LLM reasoning, and planning.
Monte Carlo Planning with Large Language Model for Text-Based Game Agents
Zijing Shi, Meng Fang, Ling Chen
ICLR 2025 · Project
Large Language Models Are Neurosymbolic Reasoners
Meng Fang*, Shilong Deng*, Yudi Zhang*, Zijing Shi, Ling Chen, Mykola Pechenizkiy, Jun Wang
AAAI 2024 · Code
Human-Guided Moral Decision Making in Text-based Games
Zijing Shi, Meng Fang, Ling Chen, Yali Du, Jun Wang
AAAI 2024: Safe, Robut, and Responsible AI (SRRAI)
A Minimal Approach for Natural Language Action Space in Text-based Games
Dongwon Kelvin Ryu, Meng Fang, Shirui Pan, Gholamreza Haffari, Ehsan Shareghi
CoNLL 2023 · Code
Stay Moral and Explore: Learn to Behave Morally in Text-based Games
Zijing Shi*, Meng Fang*, Yunqiu Xu, Ling Chen, Yali Du
ICLR 2023
Self-imitation Learning for Action Generation in Text-based Games
Zijing Shi, Yunqiu Xu, Meng Fang, Ling Chen
EACL 2023
Perceiving the World: Question-guided Reinforcement Learning for Text-based Games
Yunqiu Xu, Meng Fang, Ling Chen, Yali Du, Joey Tianyi Zhou, Chengqi Zhang
ACL 2022 · Code
Fire Burns, Sword Cuts: Commonsense Inductive Bias for Exploration in Text-based Games
Dongwon Kelvin Ryu, Ehsan Shareghi, Meng Fang, Yunqiu Xu, Shirui Pan, Reza Haf
ACL 2022 (Short) · Code
Generalization in Text-based Games via Hierarchical Reinforcement Learning
Yunqiu Xu, Meng Fang, Ling Chen, Yali Du, Chengqi Zhang
EMNLP 2021 (Findings) · Code
Deep Reinforcement Learning with Stacked Hierarchical Attention for Text-based Games
Yunqiu Xu*, Meng Fang*, Ling Chen, Yali Du, Joey Tianyi Zhou, Chengqi Zhang
NeurIPS 2020 · Code
Deep Reinforcement Learning with Transformers for Text Adventure Games
Yunqiu Xu, Ling Chen, Meng Fang, Yang Wang, Chengqi Zhang
IEEE Conference on Games (CoG) 2020
🎮 Video Games
Research on visual game agents and game benchmarks, including generalization, continual reinforcement learning, and safe reinforcement learning in embodied environments.
HASARD: A Benchmark for Vision-Based Safe Reinforcement Learning in Embodied Agents
Tristan Tomilin, Meng Fang, Mykola Pechenizkiy
ICLR 2025 · Project
COOM: A Game Benchmark for Continual Reinforcement Learning
Tristan Tomilin, Meng Fang, Yudi Zhang, Mykola Pechenizkiy
NeurIPS 2023
LevDoom: A Benchmark for Generalization on Level Difficulty in Reinforcement Learning
Tristan Tomilin, Tianhong Dai, Meng Fang, Mykola Pechenizkiy
CoG 2022 · Code