{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/adaptive-action-duration-with-contextual","title":"Adaptive Action Duration with Contextual Bandits for Deep Reinforcement Learning in Dynamic Environments","arxiv_id":"2507.00030","date":"2025-06-17","proceeding":null,"authors":["Abhishek Verma","Nallarasan V","Balaraman Ravindran"],"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.","url_abs":"https://arxiv.org/abs/2507.00030v1","url_pdf":"https://arxiv.org/pdf/2507.00030v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"adaptive-action-duration-with-contextual","repo_url":"https://github.com/abhi460729/Action-Duration-with-Contextual-Bandits-for-Deep-Reinforcement-Learning-in-Dynamic-Environments","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"atari-games","task_name":"Atari Games"},{"task_slug":"board-games","task_name":"Board Games"},{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"multi-armed-bandits","task_name":"Multi-Armed Bandits"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-atari-games","task_name":"Reinforcement Learning (Atari Games)"},{"task_slug":"sequential-decision-making","task_name":"Sequential Decision Making"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/reinforcement-learning-atari-games-on","task":"Reinforcement Learning (Atari Games)","dataset":"Seaquest - OpenAI Gym","model":"BanditDQN","rank_in_archive_order":1,"of":1,"metrics":{"Average Return":"87 ± 45"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}