Timezone: »

 
Poster
Batch Value-function Approximation with Only Realizability
Tengyang Xie · Nan Jiang

Wed Jul 21 09:00 AM -- 11:00 AM (PDT) @ Virtual

We make progress in a long-standing problem of batch reinforcement learning (RL): learning Q* from an exploratory and polynomial-sized dataset, using a realizable and otherwise arbitrary function class. In fact, all existing algorithms demand function-approximation assumptions stronger than realizability, and the mounting negative evidence has led to a conjecture that sample-efficient learning is impossible in this setting (Chen & Jiang, 2019). Our algorithm, BVFT, breaks the hardness conjecture (albeit under a stronger notion of exploratory data) via a tournament procedure that reduces the learning problem to pairwise comparison, and solves the latter with the help of a state-action-space partition constructed from the compared functions. We also discuss how BVFT can be applied to model selection among other extensions and open problems.

Author Information

Tengyang Xie (University of Illinois at Urbana-Champaign)
Nan Jiang (University of Illinois at Urbana-Champaign)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors