Targeted Data Acquisition for Evolving Negotiation Agents

by   Minae Kwon, et al.

Successful negotiators must learn how to balance optimizing for self-interest and cooperation. Yet current artificial negotiation agents often heavily depend on the quality of the static datasets they were trained on, limiting their capacity to fashion an adaptive response balancing self-interest and cooperation. For this reason, we find that these agents can achieve either high utility or cooperation, but not both. To address this, we introduce a targeted data acquisition framework where we guide the exploration of a reinforcement learning agent using annotations from an expert oracle. The guided exploration incentivizes the learning agent to go beyond its static dataset and develop new negotiation strategies. We show that this enables our agents to obtain higher-reward and more Pareto-optimal solutions when negotiating with both simulated and human partners compared to standard supervised learning and reinforcement learning methods. This trend additionally holds when comparing agents using our targeted data acquisition framework to variants of agents trained with a mix of supervised learning and reinforcement learning, or to agents using tailored reward functions that explicitly optimize for utility and Pareto-optimality.


page 6

page 13


A Cooperation Graph Approach for Multiagent Sparse Reward Reinforcement Learning

Multiagent reinforcement learning (MARL) can solve complex cooperative t...

Reward-Conditioned Policies

Reinforcement learning offers the promise of automating the acquisition ...

Prioritized Guidance for Efficient Multi-Agent Reinforcement Learning Exploration

Exploration efficiency is a challenging problem in multi-agent reinforce...

Exploration and Incentives in Reinforcement Learning

How do you incentivize self-interested agents to explore when they prefe...

Positive-Unlabeled Reward Learning

Learning reward functions from data is a promising path towards achievin...

Maintaining cooperation in complex social dilemmas using deep reinforcement learning

Social dilemmas are situations where individuals face a temptation to in...

Loss aversion fosters coordination among independent reinforcement learners

We study what are the factors that can accelerate the emergence of colla...