{"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/policy-optimization-with-penalized-point","title":"Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization","arxiv_id":"1807.00442","date":"2018-07-02","proceeding":null,"authors":["Xiangxiang Chu"],"abstract":"As the most successful variant and improvement for Trust Region Policy\nOptimization (TRPO), proximal policy optimization (PPO) has been widely applied\nacross various domains with several advantages: efficient data utilization,\neasy implementation, and good parallelism. In this paper, a first-order\ngradient reinforcement learning algorithm called Policy Optimization with\nPenalized Point Probability Distance (POP3D), which is a lower bound to the\nsquare of total variance divergence is proposed as another powerful variant.\nFirstly, we talk about the shortcomings of several commonly used algorithms, by\nwhich our method is partly motivated. Secondly, we address to overcome these\nshortcomings by applying POP3D. Thirdly, we dive into its mechanism from the\nperspective of solution manifold. Finally, we make quantitative comparisons\namong several state-of-the-art algorithms based on common benchmarks.\nSimulation results show that POP3D is highly competitive compared with PPO.\nBesides, our code is released in https://github.com/paperwithcode/pop3d.","url_abs":"http://arxiv.org/abs/1807.00442v4","url_pdf":"http://arxiv.org/pdf/1807.00442v4.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":"policy-optimization-with-penalized-point","repo_url":"https://github.com/cxxgtxy/POP3D","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"policy-optimization-with-penalized-point","repo_url":"https://github.com/paperwithcode/pop3d","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"atari-games","task_name":"Atari Games"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"}],"methods":[{"method_slug":"entropy-regularization","method_name":"Entropy Regularization"},{"method_slug":"ppo","method_name":"PPO"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/atari-games-on-atari-2600-alien","task":"Atari Games","dataset":"Atari 2600 Alien","model":"POP3D","rank_in_archive_order":32,"of":49,"metrics":{"Score":"1510.8"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-amidar","task":"Atari Games","dataset":"Atari 2600 Amidar","model":"POP3D","rank_in_archive_order":29,"of":48,"metrics":{"Score":"729.15"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-assault","task":"Atari Games","dataset":"Atari 2600 Assault","model":"POP3D","rank_in_archive_order":27,"of":45,"metrics":{"Score":"5400.13"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-asterix","task":"Atari Games","dataset":"Atari 2600 Asterix","model":"POP3D","rank_in_archive_order":41,"of":49,"metrics":{"Score":"4310.67"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-asteroids","task":"Atari Games","dataset":"Atari 2600 Asteroids","model":"POP3D","rank_in_archive_order":24,"of":43,"metrics":{"Score":"2488.1"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-atlantis","task":"Atari Games","dataset":"Atari 2600 Atlantis","model":"POP3D","rank_in_archive_order":4,"of":42,"metrics":{"Score":"2193605.67"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-bank-heist","task":"Atari Games","dataset":"Atari 2600 Bank Heist","model":"POP3D","rank_in_archive_order":17,"of":45,"metrics":{"Score":"1212.23"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-battle-zone","task":"Atari Games","dataset":"Atari 2600 Battle Zone","model":"POP3D","rank_in_archive_order":41,"of":47,"metrics":{"Score":"15466.67"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-beam-rider","task":"Atari Games","dataset":"Atari 2600 Beam Rider","model":"POP3D","rank_in_archive_order":41,"of":49,"metrics":{"Score":"4549"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-bowling","task":"Atari Games","dataset":"Atari 2600 Bowling","model":"POP3D","rank_in_archive_order":38,"of":44,"metrics":{"Score":"38.99"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-boxing","task":"Atari Games","dataset":"Atari 2600 Boxing","model":"POP3D","rank_in_archive_order":23,"of":45,"metrics":{"Score":"97.23"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-breakout","task":"Atari Games","dataset":"Atari 2600 Breakout","model":"POP3D","rank_in_archive_order":21,"of":58,"metrics":{"Score":"458.41"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-centipede","task":"Atari Games","dataset":"Atari 2600 Centipede","model":"POP3D","rank_in_archive_order":43,"of":45,"metrics":{"Score":"3315.44"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-chopper-command","task":"Atari Games","dataset":"Atari 2600 Chopper Command","model":"POP3D","rank_in_archive_order":26,"of":45,"metrics":{"Score":"6308.33"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-crazy-climber","task":"Atari Games","dataset":"Atari 2600 Crazy Climber","model":"POP3D","rank_in_archive_order":30,"of":49,"metrics":{"Score":"120247.33"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-demon-attack","task":"Atari Games","dataset":"Atari 2600 Demon Attack","model":"POP3D","rank_in_archive_order":30,"of":46,"metrics":{"Score":"61147.33"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-double-dunk","task":"Atari Games","dataset":"Atari 2600 Double Dunk","model":"POP3D","rank_in_archive_order":41,"of":43,"metrics":{"Score":"-7.89"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-enduro","task":"Atari Games","dataset":"Atari 2600 Enduro","model":"POP3D","rank_in_archive_order":35,"of":48,"metrics":{"Score":"459.85"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-fishing-derby","task":"Atari Games","dataset":"Atari 2600 Fishing Derby","model":"POP3D","rank_in_archive_order":23,"of":44,"metrics":{"Score":"28.99"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-freeway","task":"Atari Games","dataset":"Atari 2600 Freeway","model":"POP3D","rank_in_archive_order":47,"of":59,"metrics":{"Score":"21.21"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-frostbite","task":"Atari Games","dataset":"Atari 2600 Frostbite","model":"POP3D","rank_in_archive_order":45,"of":53,"metrics":{"Score":"316.87"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-gopher","task":"Atari Games","dataset":"Atari 2600 Gopher","model":"POP3D","rank_in_archive_order":36,"of":43,"metrics":{"Score":"6207"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-gravitar","task":"Atari Games","dataset":"Atari 2600 Gravitar","model":"POP3D","rank_in_archive_order":28,"of":53,"metrics":{"Score":"557.17"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-ice-hockey","task":"Atari Games","dataset":"Atari 2600 Ice Hockey","model":"POP3D","rank_in_archive_order":41,"of":43,"metrics":{"Score":"-4.12"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-james-bond","task":"Atari Games","dataset":"Atari 2600 James Bond","model":"POP3D","rank_in_archive_order":38,"of":45,"metrics":{"Score":"358.54"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-kangaroo","task":"Atari Games","dataset":"Atari 2600 Kangaroo","model":"POP3D","rank_in_archive_order":30,"of":47,"metrics":{"Score":"3891.67"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-krull","task":"Atari Games","dataset":"Atari 2600 Krull","model":"POP3D","rank_in_archive_order":32,"of":45,"metrics":{"Score":"7715.68"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-kung-fu-master","task":"Atari Games","dataset":"Atari 2600 Kung-Fu Master","model":"POP3D","rank_in_archive_order":29,"of":43,"metrics":{"Score":"33728"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-montezumas-revenge","task":"Atari Games","dataset":"Atari 2600 Montezuma's Revenge","model":"POP3D","rank_in_archive_order":46,"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":"POP3D","rank_in_archive_order":37,"of":47,"metrics":{"Score":"1683.87"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-name-this-game","task":"Atari Games","dataset":"Atari 2600 Name This Game","model":"POP3D","rank_in_archive_order":37,"of":43,"metrics":{"Score":"6065.63"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-pitfall","task":"Atari Games","dataset":"Atari 2600 Pitfall!","model":"POP3D","rank_in_archive_order":9,"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":"POP3D","rank_in_archive_order":26,"of":52,"metrics":{"Score":"20.5"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-private-eye","task":"Atari Games","dataset":"Atari 2600 Private Eye","model":"POP3D","rank_in_archive_order":50,"of":52,"metrics":{"Score":"79.67"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-qbert","task":"Atari Games","dataset":"Atari 2600 Q*Bert","model":"POP3D","rank_in_archive_order":25,"of":57,"metrics":{"Score":"15396.67"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-river-raid","task":"Atari Games","dataset":"Atari 2600 River Raid","model":"POP3D","rank_in_archive_order":31,"of":41,"metrics":{"Score":"8052.23"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-road-runner","task":"Atari Games","dataset":"Atari 2600 Road Runner","model":"POP3D","rank_in_archive_order":28,"of":44,"metrics":{"Score":"44679.67"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-robotank","task":"Atari Games","dataset":"Atari 2600 Robotank","model":"POP3D","rank_in_archive_order":40,"of":42,"metrics":{"Score":"4.6"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-seaquest","task":"Atari Games","dataset":"Atari 2600 Seaquest","model":"POP3D","rank_in_archive_order":40,"of":57,"metrics":{"Score":"1807.47"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-space-invaders","task":"Atari Games","dataset":"Atari 2600 Space Invaders","model":"POP3D","rank_in_archive_order":42,"of":55,"metrics":{"Score":"1216.15"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-star-gunner","task":"Atari Games","dataset":"Atari 2600 Star Gunner","model":"POP3D","rank_in_archive_order":34,"of":43,"metrics":{"Score":"48984"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-tennis","task":"Atari Games","dataset":"Atari 2600 Tennis","model":"POP3D","rank_in_archive_order":41,"of":43,"metrics":{"Score":"-8.32"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-time-pilot","task":"Atari Games","dataset":"Atari 2600 Time Pilot","model":"POP3D","rank_in_archive_order":42,"of":44,"metrics":{"Score":"3770.33"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-tutankham","task":"Atari Games","dataset":"Atari 2600 Tutankham","model":"POP3D","rank_in_archive_order":19,"of":44,"metrics":{"Score":"241.21"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-up-and-down","task":"Atari Games","dataset":"Atari 2600 Up and Down","model":"POP3D","rank_in_archive_order":13,"of":44,"metrics":{"Score":"242701.51"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-venture","task":"Atari Games","dataset":"Atari 2600 Venture","model":"POP3D","rank_in_archive_order":40,"of":55,"metrics":{"Score":"36.33"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-video-pinball","task":"Atari Games","dataset":"Atari 2600 Video Pinball","model":"POP3D","rank_in_archive_order":38,"of":42,"metrics":{"Score":"37780.7"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-wizard-of-wor","task":"Atari Games","dataset":"Atari 2600 Wizard of Wor","model":"POP3D","rank_in_archive_order":33,"of":41,"metrics":{"Score":"4704"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-zaxxon","task":"Atari Games","dataset":"Atari 2600 Zaxxon","model":"POP3D","rank_in_archive_order":29,"of":41,"metrics":{"Score":"9472"},"uses_additional_data":false},{"leaderboard":"/sota/mujoco-games-on-halfcheetah","task":"MuJoCo Games","dataset":"HalfCheetah","model":"POP3D","rank_in_archive_order":1,"of":1,"metrics":{"Mean":"3184.54"},"uses_additional_data":false},{"leaderboard":"/sota/mujoco-games-on-hopper","task":"MuJoCo Games","dataset":"Hopper","model":"POP3D","rank_in_archive_order":1,"of":1,"metrics":{"Mean":"1452.09"},"uses_additional_data":false},{"leaderboard":"/sota/mujoco-games-on-inverteddoublependulum","task":"MuJoCo Games","dataset":"InvertedDoublePendulum","model":"POP3D","rank_in_archive_order":1,"of":1,"metrics":{"Mean":"4907.64"},"uses_additional_data":false},{"leaderboard":"/sota/mujoco-games-on-invertedpendulum","task":"MuJoCo Games","dataset":"InvertedPendulum","model":"POP3D","rank_in_archive_order":1,"of":1,"metrics":{"Mean":"741.94"},"uses_additional_data":false},{"leaderboard":"/sota/mujoco-games-on-reacher","task":"MuJoCo Games","dataset":"Reacher","model":"POP3D","rank_in_archive_order":1,"of":1,"metrics":{"Mean":"-4.29"},"uses_additional_data":false},{"leaderboard":"/sota/mujoco-games-on-swimmer","task":"MuJoCo Games","dataset":"Swimmer","model":"POP3D","rank_in_archive_order":1,"of":1,"metrics":{"Mean":"111.08"},"uses_additional_data":false},{"leaderboard":"/sota/mujoco-games-on-walker2d","task":"MuJoCo Games","dataset":"Walker2d","model":"POP3D","rank_in_archive_order":2,"of":2,"metrics":{"Mean":"3966.01"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}