Credit Assignment
Overview
Credit assignment asks which decisions or components contributed to a success or failure, so learning can reinforce useful behavior and correct mistakes. Common approaches estimate counterfactual or marginal contributions, trace dependencies through interaction graphs, or localize rewards to steps, segments, tokens, or spatial regions. These methods are used in cooperative reinforcement learning, multi-turn LLM and tool-using agents, embodied control, and neural learning, with evaluations ranging from task success and reasoning benchmarks to attribution accuracy. The central tension is that finer-grained signals can improve learning but are costly or noisy, while dense intermediate rewards may misdirect updates when they do not reliably reflect causal contribution.
Latest papers
71 papers24 papers in the last four weeks, up 200% on the four weeks before. 0.1% of all new papers.