{"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/causal-reasoning-from-meta-reinforcement","title":"Causal Reasoning from Meta-reinforcement Learning","arxiv_id":"1901.08162","date":"2019-01-23","proceeding":"ICLR 2019 5","authors":["Ishita Dasgupta","Jane Wang","Silvia Chiappa","Jovana Mitrovic","Pedro Ortega","David Raposo","Edward Hughes","Peter Battaglia","Matthew Botvinick","Zeb Kurth-Nelson"],"abstract":"Discovering and exploiting the causal structure in the environment is a\ncrucial challenge for intelligent agents. Here we explore whether causal\nreasoning can emerge via meta-reinforcement learning. We train a recurrent\nnetwork with model-free reinforcement learning to solve a range of problems\nthat each contain causal structure. We find that the trained agent can perform\ncausal reasoning in novel situations in order to obtain rewards. The agent can\nselect informative interventions, draw causal inferences from observational\ndata, and make counterfactual predictions. Although established formal causal\nreasoning algorithms also exist, in this paper we show that such reasoning can\narise from model-free reinforcement learning, and suggest that causal reasoning\nin complex settings may benefit from the more end-to-end learning-based\napproaches presented here. This work also offers new strategies for structured\nexploration in reinforcement learning, by providing agents with the ability to\nperform -- and interpret -- experiments.","url_abs":"http://arxiv.org/abs/1901.08162v1","url_pdf":"http://arxiv.org/pdf/1901.08162v1.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":"causal-reasoning-from-meta-reinforcement","repo_url":"https://github.com/kantneel/causal-metarl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"meta-reinforcement-learning","task_name":"Meta Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":null,"task_name":"counterfactual"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1901.08162","atlas_url":"https://app.syntology.ai/?focus=1901.08162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.08162"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/kantneel/causal-metarl","reach":null}],"summary":{"ran_fixture":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"1a436fc4be34ee8a","entry":"get_permuted_adj_mats","repo":"kantneel/causal-metarl","repo_kind":"listed","path":"src/causal.py","file_url":"https://github.com/kantneel/causal-metarl/blob/HEAD/src/causal.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1a436fc4be34ee8a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}