Can I read On Value Functions and the Agent-Environment Boundary on EtoBox?

On Value Functions and the Agent-Environment Boundary by Jiang, Nan is a scholarly article available to read on EtoBox.

What is On Value Functions and the Agent-Environment Boundary about?

When function approximation is deployed in reinforcement learning (RL), the same problem may be formulated in different ways, often by treating a pre-processing step as a part of the environment or as part of the agent. As a consequence, fundamental concepts in RL, such as (optimal) value functions, are not uniquely defined as they depend on where we draw this agent-environment boundary, causing problems in theoretical analyses that provide optimality guarantees. We address this issue via a simple and novel boundary-invariant analysis of Fitted Q-Iteration, a representative RL algorithm, where the assumptions and the guarantees are invariant to the choice of boundary. We also discuss closely related issues on state resetting and Monte-Carlo Tree Search, deterministic vs stochastic systems, imitation learning, and the verifiability of theoretical assumptions from data.

Author

Jiang, Nan

Published

2019

Language

EN