Adaptive Action Duration With Contextual Bandits For Deep Reinforcement Learning In Dynamic Environments

Abstract

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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyverma2025adaptive

Related papers

• Dynamic Learning Rate For Deep Reinforcement Learning: A Bandit Approach (2024)0.00
• Control-optimized Deep Reinforcement Learning For Artificially Intelligent Autonomous Systems (2025)0.00
• On Improving Deep Reinforcement Learning For Pomdps (2017)0.00
• Dynamics-adaptive Continual Reinforcement Learning Via Progressive Contextualization (2022)7.16
• Adapting Behaviour For Learning Progress (2019)0.00
• A Human Mixed Strategy Approach To Deep Reinforcement Learning (2018)7.50
• A Bandit Framework For Optimal Selection Of Reinforcement Learning Agents (2019)0.00
• Efficient Exploration In Deep Reinforcement Learning: A Novel Bayesian Actor-critic Algorithm (2024)0.00