{"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/dex-incremental-learning-for-complex","title":"Dex: Incremental Learning for Complex Environments in Deep Reinforcement Learning","arxiv_id":"1706.05749","date":"2017-06-19","proceeding":null,"authors":["Nick Erickson","Qi Zhao"],"abstract":"This paper introduces Dex, a reinforcement learning environment toolkit\nspecialized for training and evaluation of continual learning methods as well\nas general reinforcement learning problems. We also present the novel continual\nlearning method of incremental learning, where a challenging environment is\nsolved using optimal weight initialization learned from first solving a similar\neasier environment. We show that incremental learning can produce vastly\nsuperior results than standard methods by providing a strong baseline method\nacross ten Dex environments. We finally develop a saliency method for\nqualitative analysis of reinforcement learning, which shows the impact\nincremental learning has on network attention.","url_abs":"http://arxiv.org/abs/1706.05749v1","url_pdf":"http://arxiv.org/pdf/1706.05749v1.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":"dex-incremental-learning-for-complex","repo_url":"https://github.com/innixma/dex","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"general-reinforcement-learning","task_name":"General Reinforcement Learning"},{"task_slug":"incremental-learning","task_name":"Incremental Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}