Timezone: »

Constrained episodic reinforcement learning in concave-convex and knapsack settings
Kianté Brantley · Miro Dudik · Thodoris Lykouris · Sobhan Miryoosefi · Max Simchowitz · Aleksandrs Slivkins · Wen Sun

Mon Dec 07 09:00 PM -- 11:00 PM (PST) @ Poster Session 0 #163

We propose an algorithm for tabular episodic reinforcement learning with constraints. We provide a modular analysis with strong theoretical guarantees for settings with concave rewards and convex constraints, and for settings with hard constraints (knapsacks). Most of the previous work in constrained reinforcement learning is limited to linear constraints, and the remaining work focuses on either the feasibility question or settings with a single episode. Our experiments demonstrate that the proposed algorithm significantly outperforms these approaches in existing constrained episodic environments.

Author Information

Kianté Brantley (The University of Maryland College Park)
Miro Dudik (Microsoft Research)
Thodoris Lykouris (Microsoft Research NYC)
Sobhan Miryoosefi (Princeton University)
Max Simchowitz (Berkeley)
Aleksandrs Slivkins (Microsoft Research)
Wen Sun (Microsoft Research NYC)

More from the Same Authors