{"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/action-grammars-a-cognitive-model-for","title":"Semantic RL with Action Grammars: Data-Efficient Learning of Hierarchical Task Abstractions","arxiv_id":"1907.12477","date":"2019-07-29","proceeding":null,"authors":["Robert Tjarko Lange","Aldo Faisal"],"abstract":"Hierarchical Reinforcement Learning algorithms have successfully been applied to temporal credit assignment problems with sparse reward signals. However, state-of-the-art algorithms require manual specification of sub-task structures, a sample inefficient exploration phase or lack semantic interpretability. Humans, on the other hand, efficiently detect hierarchical sub-structures induced by their surroundings. It has been argued that this inference process universally applies to language, logical reasoning as well as motor control. Therefore, we propose a cognitive-inspired Reinforcement Learning architecture which uses grammar induction to identify sub-goal policies. By treating an on-policy trajectory as a sentence sampled from the policy-conditioned language of the environment, we identify hierarchical constituents with the help of unsupervised grammatical inference. The resulting set of temporal abstractions is called action grammar (Pastra & Aloimonos, 2012) and unifies symbolic and connectionist approaches to Reinforcement Learning. It can be used to facilitate efficient imitation, transfer and online learning.","url_abs":"https://arxiv.org/abs/1907.12477v2","url_pdf":"https://arxiv.org/pdf/1907.12477v2.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":"action-grammars-a-cognitive-model-for","repo_url":"https://github.com/RobertTLange/action-grammars-hrl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"hierarchical-reinforcement-learning","task_name":"Hierarchical Reinforcement Learning"},{"task_slug":"logical-reasoning","task_name":"Logical Reasoning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1907.12477","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}