Parallel Bandit Architecture Based On Laser Chaos For Reinforcement Learning

Abstract

Accelerating artificial intelligence by photonics is an active field of study aiming to exploit the unique properties of photons. Reinforcement learning is an important branch of machine learning, and photonic decision-making principles have been demonstrated with respect to the multi-armed bandit problems. However, reinforcement learning could involve a massive number of states, unlike previously demonstrated bandit problems where the number of states is only one. Q-learning is a well-known approach in reinforcement learning that can deal with many states. The architecture of Q-learning, however, does not fit well photonic implementations due to its separation of update rule and the action selection. In this study, we organize a new architecture for multi-state reinforcement learning as a parallel array of bandit problems in order to benefit from photonic decision-makers, which we call parallel bandit architecture for reinforcement learning or PBRL in short. Taking a cart-pole balanci

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyurushibara2022parallel

Related papers

• Bandit Approach To Conflict-free Multi-agent Q-learning In View Of Photonic Implementation (2022)0.00
• Scalable Photonic Reinforcement Learning By Time-division Multiplexing Of Laser Chaos (2018)13.05
• Decentralized Multi-agent Reinforcement Learning Algorithm Using A Cluster-synchronized Laser Network (2024)0.00
• An Optical Control Environment For Benchmarking Reinforcement Learning Algorithms (2022)0.00
• Hybrid Quantum-classical Algorithm For Near-optimal Planning In Pomdps (2025)0.00
• A Bandit Framework For Optimal Selection Of Reinforcement Learning Agents (2019)0.00
• Towards Multi-agent Reinforcement Learning Using Quantum Boltzmann Machines (2021)0.00
• Laser Learning Environment: A New Environment For Coordination-critical Multi-agent Tasks (2024)0.00