Recurrent Reinforcement Learning: A Hybrid Approach

TL;DR

This paper introduces a hybrid deep learning approach combining supervised RNN/LSTM models with reinforcement learning DQNs to better handle partially observable states in complex decision-making tasks, showing improved performance.

Contribution

It proposes a novel hybrid model that jointly trains RNN/LSTM for state representation with DQN for control, addressing partial observability with minimal domain knowledge.

Findings

Outperforms previous state-of-the-art methods in mailing campaign tasks

Effectively captures long-term dependencies in state representations

Demonstrates the advantage of joint training of SL and RL components

Abstract

Successful applications of reinforcement learning in real-world problems often require dealing with partially observable states. It is in general very challenging to construct and infer hidden states as they often depend on the agent's entire interaction history and may require substantial domain knowledge. In this work, we investigate a deep-learning approach to learning the representation of states in partially observable tasks, with minimal prior knowledge of the domain. In particular, we propose a new family of hybrid models that combines the strength of both supervised learning (SL) and reinforcement learning (RL), trained in a joint fashion: The SL component can be a recurrent neural networks (RNN) or its long short-term memory (LSTM) version, which is equipped with the desired property of being able to capture long-term dependency on history, thus providing an effective way of learning the representation of hidden states. The RL component is a deep Q-network (DQN) that learns to optimize the control for maximizing long-term rewards. Extensive experiments in a direct mailing campaign problem demonstrate the effectiveness and advantages of the proposed approach, which performs the best among a set of previous state-of-the-art methods.