A Generalist Hanabi Agent

arXiv:2503.14555 · cs.MA, cs.AI · Submitted 2025-03-17 · Read on arXiv

cs.MA, cs.AI

Submitted: 2025-03-17

Updated: 2026-10-09

Code: https://github.com/hengyuan-hu/instruct-rl

Terminology

• Benchmark — 1× in this paper · explained in 2 episodes
• Multi-Agent Reinforcement Learning (MARL) — 1× in this paper · explained in 4 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes

Sources

• Open Problems in Cooperative AI
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Simplified Action Decoder for Deep Multi-Agent Reinforcement Learning
• Off-Belief Learning
• Scaling Laws for Neural Language Models
• Any-Play: An Intrinsic Augmentation for Zero-Shot Coordination
• Learning Intuitive Policies Using Action Features
• Enhancing Text-based Reinforcement Learning Agents with Commonsense Knowledge
• GPT-4 Technical Report
• DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
• Prioritized Experience Replay
• Pre-trained Language Models as Prior Knowledge for Playing Text-based Games
• Open-Ended Learning Leads to Generally Capable Agents
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• Learn How to Cook a New Recipe in a New House: Using Map Familiarization, Curriculum Learning, and Bandit Feedback to Learn Families of Text-Based Adventure Games
• Counting to Explore and Generalize in Text-based Games

Related papers

• Highway Congestion Reduction through Reinforcement Learning Based Eulerian Headway Control
• ORACLE-SWE: Quantifying the Contribution of Critical Information Signals on SWE Agents
• You Only Align Once: Propagating Cooperative Behaviors in Multi-Agent Systems through Seed Agents
• Deny Without Disabling: Authorization-Paired Evaluation and Control for Multi-Agent Systems
• MA-SAPO: Multi-Agent Reasoning for Score-Aware Prompt Optimization
• PeroMAS: A Multi-agent System of Perovskite Material Discovery