{"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/graph-constrained-reinforcement-learning-for-1","title":"Graph Constrained Reinforcement Learning for Natural Language Action Spaces","arxiv_id":"2001.08837","date":"2020-01-23","proceeding":"ICLR 2020 1","authors":["Prithviraj Ammanabrolu","Matthew Hausknecht"],"abstract":"Interactive Fiction games are text-based simulations in which an agent interacts with the world purely through natural language. They are ideal environments for studying how to extend reinforcement learning agents to meet the challenges of natural language understanding, partial observability, and action generation in combinatorially-large text-based action spaces. We present KG-A2C, an agent that builds a dynamic knowledge graph while exploring and generates actions using a template-based action space. We contend that the dual uses of the knowledge graph to reason about game state and to constrain natural language generation are the keys to scalable exploration of combinatorially large natural language actions. Results across a wide variety of IF games show that KG-A2C outperforms current IF agents despite the exponential increase in action space size.","url_abs":"https://arxiv.org/abs/2001.08837v1","url_pdf":"https://arxiv.org/pdf/2001.08837v1.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":"graph-constrained-reinforcement-learning-for-1","repo_url":"https://github.com/rajammanabrolu/KG-A2C","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-generation","task_name":"Action Generation"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2001.08837","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.08837"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rajammanabrolu/KG-A2C","reach":null}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"1a3d66acc2e2d2a6","entry":"ActionDrQA","repo":"rajammanabrolu/KG-A2C","repo_kind":"official","path":"kga2c/models.py","file_url":"https://github.com/rajammanabrolu/KG-A2C/blob/HEAD/kga2c/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1a3d66acc2e2d2a6"}},{"code_sha256_prefix":"70278f47af24045d","entry":"GAT","repo":"rajammanabrolu/KG-A2C","repo_kind":"official","path":"kga2c/models.py","file_url":"https://github.com/rajammanabrolu/KG-A2C/blob/HEAD/kga2c/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"70278f47af24045d"}},{"code_sha256_prefix":"47fbd850c86f3d8d","entry":"KGA2C","repo":"rajammanabrolu/KG-A2C","repo_kind":"official","path":"kga2c/models.py","file_url":"https://github.com/rajammanabrolu/KG-A2C/blob/HEAD/kga2c/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"47fbd850c86f3d8d"}},{"code_sha256_prefix":"d008369b6f6f82b1","entry":"ObjectDecoder","repo":"rajammanabrolu/KG-A2C","repo_kind":"official","path":"kga2c/models.py","file_url":"https://github.com/rajammanabrolu/KG-A2C/blob/HEAD/kga2c/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d008369b6f6f82b1"}},{"code_sha256_prefix":"be36306b9abf0531","entry":"StateNetwork","repo":"rajammanabrolu/KG-A2C","repo_kind":"official","path":"kga2c/models.py","file_url":"https://github.com/rajammanabrolu/KG-A2C/blob/HEAD/kga2c/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"be36306b9abf0531"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}