Please note: This PhD seminar will take place in DC 2584 and online.
Shuhui Zhu, PhD candidate
David R. Cheriton School of Computer Science
Supervisor: Professor Pascal Poupart
The partial alignment and conflict of autonomous agents lead to mixed-motive scenarios in many real-world applications. However, agents may fail to cooperate in practice even when cooperation yields a better outcome. One well-known reason for this failure comes from non-credible commitments. To facilitate commitments among agents for better cooperation, we define Markov Commitment Games (MCGs), a variant of commitment games, where agents can voluntarily commit to their proposed future plans. Based on MCGs, we propose a learnable commitment protocol via policy gradients. We further propose incentive-compatible learning to accelerate convergence to equilibria with better social welfare. Experimental results in challenging mixed-motive tasks demonstrate faster empirical convergence and higher returns for our method compared with its counterparts.
To attend this PhD seminar is person, please go to DC 2584. You can also attend virtually using Zoom.