We consider a twoagent MDP framework where agents repeatedly solve a task in a collaborative setting. We study the problem of designing a learning algorithm for the first agent (A1) that facilitates a successful collaboration even in cases when the second agent (A2) is adapting its policy in an unknown way. The key challenge in our setting is that the first agent faces nonstationarity in rewards and transitions because of the adaptive behavior of the second agent.
We design novel online learning algorithms for agent A1 whose regret decays as $O(T^{1\frac{3}{7} \cdot \alpha})$ with $T$ learning episodes provided that the magnitude of agent A2's policy changes between any two consecutive episodes are upper bounded by $O(T^{\alpha})$. Here, the parameter $\alpha$ is assumed to be strictly greater than $0$, and we show that this assumption is necessary provided that the {\em learning parity with noise} problem is computationally hard. We show that sublinear regret of agent A1 further implies nearoptimality of the agents' joint return for MDPs that manifest the properties of a {\em smooth} game.
Author Information
Goran Radanovic (Harvard University)
Rati Devidze (Max Planck Institute for Software Systems)
David Parkes (Harvard University)
Adish Singla (Max Planck Institute (MPISWS))
Related Events (a corresponding poster, oral, or spotlight)

2019 Oral: Learning to Collaborate in Markov Decision Processes »
Tue Jun 11th 02:35  02:40 PM Room Room 104
More from the Same Authors

2019 Poster: Fairness without Harm: Decoupled Classifiers with Preference Guarantees »
Berk Ustun · Yang Liu · David Parkes 
2019 Oral: Fairness without Harm: Decoupled Classifiers with Preference Guarantees »
Berk Ustun · Yang Liu · David Parkes 
2019 Poster: Efficient learning of smooth probability functions from Bernoulli tests with guarantees »
Paul Rolland · Ali Kavis · Alexander Niklaus Immer · Adish Singla · Volkan Cevher 
2019 Oral: Efficient learning of smooth probability functions from Bernoulli tests with guarantees »
Paul Rolland · Ali Kavis · Alexander Niklaus Immer · Adish Singla · Volkan Cevher 
2019 Poster: Optimal Auctions through Deep Learning »
Paul Duetting · Zhe Feng · Harikrishna Narasimhan · David Parkes · Sai Srivatsa Ravindranath 
2019 Oral: Optimal Auctions through Deep Learning »
Paul Duetting · Zhe Feng · Harikrishna Narasimhan · David Parkes · Sai Srivatsa Ravindranath