Sharing the Cost of Success: A Game for Evaluating and Learning Collaborative Multi-Agent Instruction Giving and Following Policies
In collaborative goal-oriented settings, the participants are not only interested in achieving a successful outcome, but do also implicitly negotiate the effort they put into the interaction (by adapting to each other). In this work, we propose a challenging interactive reference game that requires two players to coordinate on vision and language observations. The learning signal in this game is a score (given after playing) that takes into account the achieved goal and the players' assumed efforts during the interaction. We show that a standard Proximal Policy Optimization (PPO) setup achieves a high success rate when bootstrapped with heuristic partner behaviors that implement insights from the analysis of human-human interactions. And we find that a pairing of neural partners indeed reduces the measured joint effort when playing together repeatedly. However, we observe that in comparison to a reasonable heuristic pairing there is still room for improvement -- which invites further research in the direction of cost-sharing in collaborative interactions.
Code (1)
Similar Papers 제목 키워드 기반
Distributed Deep Reinforcement Learning for Collaborative Spectrum Sharing
Spectrum sharing among users is a fundamental problem in the management of any wireless network. In this paper, we discuss the problem of distributed spectrum collaboration without central management under general unknow…
Combinatorial OptimizationDeep Reinforcement LearningManagementQ-Learning+3Collaborative Honeypot Defense in UAV Networks: A Learning-Based Game Approach
The proliferation of unmanned aerial vehicles (UAVs) opens up new opportunities for on-demand service provisioning anywhere and anytime, but also exposes UAVs to a variety of cyber threats. Low/medium interaction honeypo…
Computational EfficiencyFairnessvalidCommunication-Efficient Actor-Critic Methods for Homogeneous Markov Games
Recent success in cooperative multi-agent reinforcement learning (MARL) relies on centralized training and policy sharing. Centralized training eliminates the issue of non-stationarity MARL yet induces large communicatio…
Multi-agent Reinforcement LearningLLM-Hanabi: Evaluating Multi-Agent Gameplays with Theory-of-Mind and Rationale Inference in Imperfect Information Collaboration Game
Effective multi-agent collaboration requires agents to infer the rationale behind others' actions, a capability rooted in Theory-of-Mind (ToM). While recent Large Language Models (LLMs) excel at logical inference, their …
MT-PingEval: Evaluating Multi-Turn Collaboration with Private Information Games
We present a scalable methodology for evaluating language models in multi-turn interactions, using a suite of collaborative games that require effective communication about private information. This enables an interactiv…