LLM-guided synthesis of reward programs yields higher task returns in cooperative multi-agent RL across Overcooked layouts with interaction bottlenecks.
Expressing arbitrary reward functions as potential- based advice
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Large Language Model Guided Incentive Aware Reward Design for Cooperative Multi-Agent Reinforcement Learning
LLM-guided synthesis of reward programs yields higher task returns in cooperative multi-agent RL across Overcooked layouts with interaction bottlenecks.