{"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/a-disembodied-developmental-robotic-agent","title":"A disembodied developmental robotic agent called Samu Bátfai","arxiv_id":"1511.02889","date":"2015-11-09","proceeding":null,"authors":["Norbert Bátfai"],"abstract":"The agent program, called Samu, is an experiment to build a disembodied\nDevRob (Developmental Robotics) chatter bot that can talk in a natural language\nlike humans do. One of the main design feature is that Samu can be interacted\nwith using only a character terminal. This is important not only for practical\naspects of Turing test or Loebner prize, but also for the study of basic\nprinciples of Developmental Robotics. Our purpose is to create a rapid\nprototype of Q-learning with neural network approximators for Samu. We sketch\nout the early stages of the development process of this prototype, where Samu's\ntask is to predict the next sentence of tales or conversations. The basic\nobjective of this paper is to reach the same results using reinforcement\nlearning with general function approximators that can be achieved by using the\nclassical Q lookup table on small input samples. The paper is closed by an\nexperiment that shows a significant improvement in Samu's learning when using\nLZW tree to narrow the number of possible Q-actions.","url_abs":"http://arxiv.org/abs/1511.02889v1","url_pdf":"http://arxiv.org/pdf/1511.02889v1.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":"a-disembodied-developmental-robotic-agent","repo_url":"https://github.com/nbatfai/amminadab","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"a-disembodied-developmental-robotic-agent","repo_url":"https://github.com/nbatfai/hezron","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"a-disembodied-developmental-robotic-agent","repo_url":"https://github.com/nbatfai/isaac","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"a-disembodied-developmental-robotic-agent","repo_url":"https://github.com/nbatfai/jacob","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"a-disembodied-developmental-robotic-agent","repo_url":"https://github.com/nbatfai/judah","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"a-disembodied-developmental-robotic-agent","repo_url":"https://github.com/nbatfai/perez","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"a-disembodied-developmental-robotic-agent","repo_url":"https://github.com/nbatfai/ram","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"a-disembodied-developmental-robotic-agent","repo_url":"https://github.com/nbatfai/samu","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"a-disembodied-developmental-robotic-agent","repo_url":"https://github.com/nbatfai/Robopsychology","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"a-disembodied-developmental-robotic-agent","repo_url":"https://github.com/nbatfai/SamuBrain","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"a-disembodied-developmental-robotic-agent","repo_url":"https://github.com/nbatfai/SamuCTuring","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"a-disembodied-developmental-robotic-agent","repo_url":"https://github.com/nbatfai/SamuKnows","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"a-disembodied-developmental-robotic-agent","repo_url":"https://github.com/nbatfai/SamuLife","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"a-disembodied-developmental-robotic-agent","repo_url":"https://github.com/nbatfai/SamuTuring","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"a-disembodied-developmental-robotic-agent","repo_url":"https://github.com/nbatfai/nahshon","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"q-learning","task_name":"Q-Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[{"method_slug":"q-learning","method_name":"Q-Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}