Negotiated Reasoning: On Provably Addressing Relative Over-generalization

Abstract

Over-generalization is a thorny issue in cognitive science, where people may become overly cautious due to past experiences. Agents in multi-agent reinforcement learning (MARL) also have been found to suffer relative over-generalization (RO) as people do and stuck to sub-optimal cooperation. Recent methods have shown that assigning reasoning ability to agents can mitigate RO algorithmically and empirically, but there has been a lack of theoretical understanding of RO, let alone designing provably RO-free methods. This paper first proves that RO can be avoided when the MARL method satisfies a consistent reasoning requirement under certain conditions. Then we introduce a novel reasoning framework, called negotiated reasoning, that first builds the connection between reasoning and RO with theoretical justifications. After that, we propose an instantiated algorithm, Stein variational negotiated reasoning (SVNR), which uses Stein variational gradient descent to derive a negotiation policy t

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keysheng2023negotiated

Related papers

• Modelling Bounded Rationality In Multi-agent Interactions By Generalized Recursive Reasoning (2019)9.23
• CURO: Curriculum Learning For Relative Overgeneralization (2022)0.00
• Probabilistic Recursive Reasoning For Multi-agent Reinforcement Learning (2019)0.00
• Mitigating Relative Over-generalization In Multi-agent Reinforcement Learning (2024)0.00
• Training Generalizable Collaborative Agents Via Strategic Risk Aversion (2026)0.00
• Iterated Reasoning With Mutual Information In Cooperative And Byzantine Decentralized Teaming (2022)0.00
• Probing Dec-pomdp Reasoning In Cooperative MARL (2026)0.00
• Optimistic Multi-agent Policy Gradient (2023)0.00