Recurrent Reinforcement Learning: A Hybrid Approach
This work addresses the problem of handling partial observability in reinforcement learning for real-world applications like marketing campaigns, but it is incremental as it builds on existing methods.
The paper tackles the challenge of partially observable states in reinforcement learning by proposing a hybrid model combining supervised learning (RNN/LSTM) and reinforcement learning (DQN) to learn state representations with minimal domain knowledge. In experiments on a direct mailing campaign problem, the approach outperforms previous state-of-the-art methods.
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.