Venue
- IJCAI-2020
Date
- 2021
Share
Balancing Individual Preferences and Shared Objectives in Multiagent Reinforcement Learning
Ishan Durugkar
Elad Liebman*
* External authors
IJCAI-2020
2021
Abstract
In multiagent reinforcement learning scenarios, it is often the case that independent agents must jointly learn to perform a cooperative task. This paper focuses on such a scenario in which agents have individual preferences regarding how to accomplish the shared task. We consider a framework for this setting which balances individual preferences against task rewards using a linear mixing scheme. In our theoretical analysis we establish that agents can reach an equilibrium that leads to optimal shared task reward even when they consider individual preferences which are not fully aligned with this task. We then empirically show, somewhat counter-intuitively, that there exist mixing schemes that outperform a purely task-oriented baseline. We further consider empirically how to optimize the mixing scheme.
Related Publications
Two desiderata of reinforcement learning (RL) algorithms are the ability to learn from relatively little experience and the ability to learn policies that generalize to a range of problem specifications. In factored state spaces, one approach towards achieving both goals is …
Robustly cooperating with unseen agents and human partners presents significant challenges due to the diverse cooperative conventions these partners may adopt. Existing Ad Hoc Teamwork (AHT) methods address this challenge by training an agent with a population of diverse tea…
We consider algorithms for learning reward functions from human preferences over pairs of trajectory segments---as used in reinforcement learning from human feedback (RLHF)---including those used to fine tune ChatGPT and other contemporary language models. Most recent work o…
JOIN US
Shape the Future of AI with Sony AI
We want to hear from those of you who have a strong desire
to shape the future of AI.
