{"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/towards-generalization-and-simplicity-in","title":"Towards Generalization and Simplicity in Continuous Control","arxiv_id":"1703.02660","date":"2017-03-08","proceeding":"NeurIPS 2017 12","authors":["Aravind Rajeswaran","Kendall Lowrey","Emanuel Todorov","Sham Kakade"],"abstract":"This work shows that policies with simple linear and RBF parameterizations\ncan be trained to solve a variety of continuous control tasks, including the\nOpenAI gym benchmarks. The performance of these trained policies are\ncompetitive with state of the art results, obtained with more elaborate\nparameterizations such as fully connected neural networks. Furthermore,\nexisting training and testing scenarios are shown to be very limited and prone\nto over-fitting, thus giving rise to only trajectory-centric policies. Training\nwith a diverse initial state distribution is shown to produce more global\npolicies with better generalization. This allows for interactive control\nscenarios where the system recovers from large on-line perturbations; as shown\nin the supplementary video.","url_abs":"http://arxiv.org/abs/1703.02660v2","url_pdf":"http://arxiv.org/pdf/1703.02660v2.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":"towards-generalization-and-simplicity-in","repo_url":"https://github.com/khansel01/nes-npg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"continuous-control","task_name":"Continuous Control"},{"task_slug":"openai-gym","task_name":"OpenAI Gym"},{"task_slug":"continuous-control","task_name":"continuous-control"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1703.02660","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}