Deep Reinforcement Learning with Quantum-inspired Experience Replay

Abstract

In this paper, a novel training paradigm inspired by quantum computation is proposed for deep reinforcement learning (DRL) with experience replay. In contrast to traditional experience replay mechanism in DRL, the proposed deep reinforcement learning with quantum-inspired experience replay (DRL-QER) adaptively chooses experiences from the replay buffer according to the complexity and the replayed times of each experience (also called transition), to achieve a balance between exploration and exploitation. In DRL-QER, transitions are first formulated in quantum representations, and then the preparation operation and the depreciation operation are performed on the transitions. In this progress, the preparation operation reflects the relationship between the temporal difference errors (TD-errors) and the importance of the experiences, while the depreciation operation is taken into account to ensure the diversity of the transitions. The experimental results on Atari 2600 games show that DRL-QER outperforms state-of-the-art algorithms such as DRL-PER and DCRL on most of these games with improved training efficiency, and is also applicable to such memory-based DRL approaches as double network and dueling network.

References in corpus (15)

• Sequence to Sequence Learning with Neural Networks
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Dueling Network Architectures for Deep Reinforcement Learning
• Quantum principal component analysis
• Efficient Learning for Deep Quantum Neural Networks
• Quantum control theory and applications: A survey
• Quantum-enhanced machine learning
• Quantum computers can search arbitrarily large databases by a single query
• Quantum reinforcement learning
• Experimental Realization of Quantum Artificial Intelligence
• Entanglement-Based Machine Learning on a Quantum Computer
• Quantum speedup for active learning agents
• Fidelity-based Probabilistic Q-learning for Control of Quantum Systems
• Basic protocols in quantum reinforcement learning with superconducting circuits
• Multiqubit and multilevel quantum reinforcement learning with quantum technologies