Adaptive Action Duration with Contextual Bandits for Deep Reinforcement Learning in Dynamic Environments
This addresses the need for flexible action execution in dynamic environments like gaming and robotics, offering a scalable solution.
The paper tackles the problem of fixed action durations in deep reinforcement learning by proposing an adaptive method using contextual bandits, resulting in significant performance improvements over static baselines in Atari 2600 games.
Deep Reinforcement Learning (DRL) has achieved remarkable success in complex sequential decision-making tasks, such as playing Atari 2600 games and mastering board games. A critical yet underexplored aspect of DRL is the temporal scale of action execution. We propose a novel paradigm that integrates contextual bandits with DRL to adaptively select action durations, enhancing policy flexibility and computational efficiency. Our approach augments a Deep Q-Network (DQN) with a contextual bandit module that learns to choose optimal action repetition rates based on state contexts. Experiments on Atari 2600 games demonstrate significant performance improvements over static duration baselines, highlighting the efficacy of adaptive temporal abstractions in DRL. This paradigm offers a scalable solution for real-time applications like gaming and robotics, where dynamic action durations are critical.