Poster
No-Regret Learning in Unknown Games with Correlated Payoffs
Pier Giuseppe Sessa · Ilija Bogunovic · Maryam Kamgarpour · Andreas Krause

Wed Dec 11th 05:00 -- 07:00 PM @ East Exhibition Hall B + C #6
in Algorithms -- Bandit Algorithms »

We consider the problem of learning to play a repeated multi-agent game with an unknown reward function. Single player online learning algorithms attain strong regret bounds when provided with full information feedback, which unfortunately is unavailable in many real-world scenarios. Bandit feedback alone, i.e., observing outcomes only for the selected action, yields substantially worse performance. In this paper, we consider a natural model where, besides a noisy measurement of the obtained reward, the player can also observe the opponents' actions. This feedback model, together with a regularity assumption on the reward function, allows us to exploit the correlations among different game outcomes by means of Gaussian processes (GPs). We propose a novel confidence-bound based bandit algorithm GP-MW, which utilizes the GP model for the reward function and runs a multiplicative weight (MW) method. We obtain novel kernel-dependent regret bounds that are comparable to the known bounds in the full information setting, while substantially improving upon the existing bandit results. We experimentally demonstrate the effectiveness of GP-MW in random matrix games, as well as real-world problems of traffic routing and movie recommendation. In our experiments, GP-MW consistently outperforms several baselines, while its performance is often comparable to methods that have access to full information feedback.

Keywords: Algorithms -> Bandit Algorithms · Algorithms -> Online Learning; Applications -> Game Playing; Probabilistic Methods -> Gaussian Processes; Theory -> Game Theory

Author Information

Pier Giuseppe Sessa (ETH Zürich)
Ilija Bogunovic (ETH Zurich)
Maryam Kamgarpour (ETH Zürich)
Andreas Krause (ETH Zurich)

More from the Same Authors