Operator Deep Q-Learning: Zero-Shot Reward Transferring in Reinforcement Learning

TL;DR

This paper introduces an operator neural network framework for reinforcement learning that enables zero-shot transfer of value functions to unseen reward functions, significantly improving adaptability in RL tasks.

Contribution

It proposes a novel operator neural network architecture for RL that allows direct approximation of reward-to-value operators, facilitating zero-shot reward transfer.

Findings

Operator networks outperform existing methods.

Framework enables zero-shot reward transfer.

Improves offline policy evaluation and optimization.

Abstract

Reinforcement learning (RL) has drawn increasing interests in recent years due to its tremendous success in various applications. However, standard RL algorithms can only be applied for single reward function, and cannot adapt to an unseen reward function quickly. In this paper, we advocate a general operator view of reinforcement learning, which enables us to directly approximate the operator that maps from reward function to value function. The benefit of learning the operator is that we can incorporate any new reward function as input and attain its corresponding value function in a zero-shot manner. To approximate this special type of operator, we design a number of novel operator neural network architectures based on its theoretical properties. Our design of operator networks outperform the existing methods and the standard design of general purpose operator network, and we demonstrate the benefit of our operator deep Q-learning framework in several tasks including reward transferring for offline policy evaluation (OPE) and reward transferring for offline policy optimization in a range of tasks.