{"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/dna-proximal-policy-optimization-with-a-dual","title":"DNA: Proximal Policy Optimization with a Dual Network Architecture","arxiv_id":"2206.10027","date":"2022-06-20","proceeding":null,"authors":["Matthew Aitchison","Penny Sweetser"],"abstract":"This paper explores the problem of simultaneously learning a value function and policy in deep actor-critic reinforcement learning models. We find that the common practice of learning these functions jointly is sub-optimal, due to an order-of-magnitude difference in noise levels between these two tasks. Instead, we show that learning these tasks independently, but with a constrained distillation phase, significantly improves performance. Furthermore, we find that the policy gradient noise levels can be decreased by using a lower \\textit{variance} return estimate. Whereas, the value learning noise level decreases with a lower \\textit{bias} estimate. Together these insights inform an extension to Proximal Policy Optimization we call \\textit{Dual Network Architecture} (DNA), which significantly outperforms its predecessor. DNA also exceeds the performance of the popular Rainbow DQN algorithm on four of the five environments tested, even under more difficult stochastic control settings.","url_abs":"https://arxiv.org/abs/2206.10027v2","url_pdf":"https://arxiv.org/pdf/2206.10027v2.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":"dna-proximal-policy-optimization-with-a-dual","repo_url":"https://github.com/maitchison/PPO","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"atari-games","task_name":"Atari Games"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dqn","method_name":"DQN"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"double-q-learning","method_name":"Double Q-learning"},{"method_slug":"dueling-network","method_name":"Dueling Network"},{"method_slug":"n-step-returns","method_name":"N-step Returns"},{"method_slug":"noisy-net","method_name":"Noisy Linear Layer"},{"method_slug":"prioritized-experience-replay","method_name":"Prioritized Experience Replay"},{"method_slug":"q-learning","method_name":"Q-Learning"},{"method_slug":"rainbow-dqn","method_name":"Rainbow DQN"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/atari-games-on-atari-2600-alien","task":"Atari Games","dataset":"Atari 2600 Alien","model":"DNA","rank_in_archive_order":17,"of":49,"metrics":{"Score":"5021"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-amidar","task":"Atari Games","dataset":"Atari 2600 Amidar","model":"DNA","rank_in_archive_order":24,"of":48,"metrics":{"Score":"1025"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-assault","task":"Atari Games","dataset":"Atari 2600 Assault","model":"DNA","rank_in_archive_order":12,"of":45,"metrics":{"Score":"16293"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-asterix","task":"Atari Games","dataset":"Atari 2600 Asterix","model":"DNA","rank_in_archive_order":14,"of":49,"metrics":{"Score":"323965"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-asteroids","task":"Atari Games","dataset":"Atari 2600 Asteroids","model":"DNA","rank_in_archive_order":6,"of":43,"metrics":{"Score":"165973"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-atlantis","task":"Atari Games","dataset":"Atari 2600 Atlantis","model":"DNA","rank_in_archive_order":18,"of":42,"metrics":{"Score":"932559"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-bank-heist","task":"Atari Games","dataset":"Atari 2600 Bank Heist","model":"DNA","rank_in_archive_order":12,"of":45,"metrics":{"Score":"1286"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-battle-zone","task":"Atari Games","dataset":"Atari 2600 Battle Zone","model":"DNA","rank_in_archive_order":9,"of":47,"metrics":{"Score":"71003"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-beam-rider","task":"Atari Games","dataset":"Atari 2600 Beam Rider","model":"DNA","rank_in_archive_order":21,"of":49,"metrics":{"Score":"20393"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-berzerk","task":"Atari Games","dataset":"Atari 2600 Berzerk","model":"DNA","rank_in_archive_order":6,"of":39,"metrics":{"Score":"19789"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-bowling","task":"Atari Games","dataset":"Atari 2600 Bowling","model":"DNA","rank_in_archive_order":8,"of":44,"metrics":{"Score":"181"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-boxing","task":"Atari Games","dataset":"Atari 2600 Boxing","model":"DNA","rank_in_archive_order":12,"of":45,"metrics":{"Score":"99.9"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-breakout","task":"Atari Games","dataset":"Atari 2600 Breakout","model":"DNA","rank_in_archive_order":17,"of":58,"metrics":{"Score":"626"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-centipede","task":"Atari Games","dataset":"Atari 2600 Centipede","model":"DNA","rank_in_archive_order":11,"of":45,"metrics":{"Score":"100194"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-chopper-command","task":"Atari Games","dataset":"Atari 2600 Chopper Command","model":"DNA","rank_in_archive_order":11,"of":45,"metrics":{"Score":"31181"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-crazy-climber","task":"Atari Games","dataset":"Atari 2600 Crazy Climber","model":"DNA","rank_in_archive_order":23,"of":49,"metrics":{"Score":"131623"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-defender","task":"Atari Games","dataset":"Atari 2600 Defender","model":"DNA","rank_in_archive_order":12,"of":21,"metrics":{"Score":"152768"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-demon-attack","task":"Atari Games","dataset":"Atari 2600 Demon Attack","model":"DNA","rank_in_archive_order":18,"of":46,"metrics":{"Score":"97909"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-double-dunk","task":"Atari Games","dataset":"Atari 2600 Double Dunk","model":"DNA","rank_in_archive_order":43,"of":43,"metrics":{"Score":"-1.3"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-enduro","task":"Atari Games","dataset":"Atari 2600 Enduro","model":"DNA","rank_in_archive_order":19,"of":48,"metrics":{"Score":"2059"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-fishing-derby","task":"Atari Games","dataset":"Atari 2600 Fishing Derby","model":"DNA","rank_in_archive_order":9,"of":44,"metrics":{"Score":"57.4"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-freeway","task":"Atari Games","dataset":"Atari 2600 Freeway","model":"DNA","rank_in_archive_order":22,"of":59,"metrics":{"Score":"33"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-frostbite","task":"Atari Games","dataset":"Atari 2600 Frostbite","model":"DNA","rank_in_archive_order":43,"of":53,"metrics":{"Score":"320"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-gopher","task":"Atari Games","dataset":"Atari 2600 Gopher","model":"DNA","rank_in_archive_order":14,"of":43,"metrics":{"Score":"80104"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-gravitar","task":"Atari Games","dataset":"Atari 2600 Gravitar","model":"DNA","rank_in_archive_order":17,"of":53,"metrics":{"Score":"2190"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-hero","task":"Atari Games","dataset":"Atari 2600 HERO","model":"DNA","rank_in_archive_order":19,"of":44,"metrics":{"Score":"24904"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-ice-hockey","task":"Atari Games","dataset":"Atari 2600 Ice Hockey","model":"DNA","rank_in_archive_order":12,"of":43,"metrics":{"Score":"7.2"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-james-bond","task":"Atari Games","dataset":"Atari 2600 James Bond","model":"DNA","rank_in_archive_order":12,"of":45,"metrics":{"Score":"14102"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-kangaroo","task":"Atari Games","dataset":"Atari 2600 Kangaroo","model":"DNA","rank_in_archive_order":12,"of":47,"metrics":{"Score":"14373"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-krull","task":"Atari Games","dataset":"Atari 2600 Krull","model":"DNA","rank_in_archive_order":13,"of":45,"metrics":{"Score":"10956"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-kung-fu-master","task":"Atari Games","dataset":"Atari 2600 Kung-Fu Master","model":"DNA","rank_in_archive_order":9,"of":43,"metrics":{"Score":"110962"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-montezumas-revenge","task":"Atari Games","dataset":"Atari 2600 Montezuma's Revenge","model":"DNA","rank_in_archive_order":48,"of":50,"metrics":{"Score":"0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-ms-pacman","task":"Atari Games","dataset":"Atari 2600 Ms. Pacman","model":"DNA","rank_in_archive_order":16,"of":47,"metrics":{"Score":"5894"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-name-this-game","task":"Atari Games","dataset":"Atari 2600 Name This Game","model":"DNA","rank_in_archive_order":12,"of":43,"metrics":{"Score":"20226"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-phoenix","task":"Atari Games","dataset":"Atari 2600 Phoenix","model":"DNA","rank_in_archive_order":8,"of":21,"metrics":{"Score":"391085"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-pitfall","task":"Atari Games","dataset":"Atari 2600 Pitfall!","model":"DNA","rank_in_archive_order":16,"of":23,"metrics":{"Score":"0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-pong","task":"Atari Games","dataset":"Atari 2600 Pong","model":"DNA","rank_in_archive_order":32,"of":52,"metrics":{"Score":"19.7"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-private-eye","task":"Atari Games","dataset":"Atari 2600 Private Eye","model":"DNA","rank_in_archive_order":45,"of":52,"metrics":{"Score":"100"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-qbert","task":"Atari Games","dataset":"Atari 2600 Q*Bert","model":"DNA","rank_in_archive_order":10,"of":57,"metrics":{"Score":"52398"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-river-raid","task":"Atari Games","dataset":"Atari 2600 River Raid","model":"DNA","rank_in_archive_order":16,"of":41,"metrics":{"Score":"16789"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-road-runner","task":"Atari Games","dataset":"Atari 2600 Road Runner","model":"DNA","rank_in_archive_order":15,"of":44,"metrics":{"Score":"61713"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-robotank","task":"Atari Games","dataset":"Atari 2600 Robotank","model":"DNA","rank_in_archive_order":16,"of":42,"metrics":{"Score":"64.8"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-seaquest","task":"Atari Games","dataset":"Atari 2600 Seaquest","model":"DNA","rank_in_archive_order":35,"of":57,"metrics":{"Score":"4146"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-skiing","task":"Atari Games","dataset":"Atari 2600 Skiing","model":"DNA","rank_in_archive_order":22,"of":23,"metrics":{"Score":"-29974"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-solaris","task":"Atari Games","dataset":"Atari 2600 Solaris","model":"DNA","rank_in_archive_order":21,"of":23,"metrics":{"Score":"2225"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-space-invaders","task":"Atari Games","dataset":"Atari 2600 Space Invaders","model":"DNA","rank_in_archive_order":30,"of":55,"metrics":{"Score":"2731"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-star-gunner","task":"Atari Games","dataset":"Atari 2600 Star Gunner","model":"DNA","rank_in_archive_order":16,"of":43,"metrics":{"Score":"104125"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-surround","task":"Atari Games","dataset":"Atari 2600 Surround","model":"DNA","rank_in_archive_order":10,"of":15,"metrics":{"Score":"5.3"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-tennis","task":"Atari Games","dataset":"Atari 2600 Tennis","model":"DNA","rank_in_archive_order":43,"of":43,"metrics":{"Score":"-10.9"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-time-pilot","task":"Atari Games","dataset":"Atari 2600 Time Pilot","model":"DNA","rank_in_archive_order":16,"of":44,"metrics":{"Score":"12774"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-tutankham","task":"Atari Games","dataset":"Atari 2600 Tutankham","model":"DNA","rank_in_archive_order":33,"of":44,"metrics":{"Score":"127"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-up-and-down","task":"Atari Games","dataset":"Atari 2600 Up and Down","model":"DNA","rank_in_archive_order":12,"of":44,"metrics":{"Score":"291934"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-venture","task":"Atari Games","dataset":"Atari 2600 Venture","model":"DNA","rank_in_archive_order":55,"of":55,"metrics":{"Score":"0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-video-pinball","task":"Atari Games","dataset":"Atari 2600 Video Pinball","model":"DNA","rank_in_archive_order":16,"of":42,"metrics":{"Score":"505392"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-wizard-of-wor","task":"Atari Games","dataset":"Atari 2600 Wizard of Wor","model":"DNA","rank_in_archive_order":13,"of":41,"metrics":{"Score":"20851"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-yars-revenge","task":"Atari Games","dataset":"Atari 2600 Yars Revenge","model":"DNA","rank_in_archive_order":5,"of":17,"metrics":{"Score":"564513"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-zaxxon","task":"Atari Games","dataset":"Atari 2600 Zaxxon","model":"DNA","rank_in_archive_order":13,"of":41,"metrics":{"Score":"22588"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2206.10027","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}