{"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/identifying-and-addressing-delusions-for","title":"Rejecting Hallucinated State Targets during Planning","arxiv_id":"2410.07096","date":"2024-10-09","proceeding":null,"authors":["Mingde Zhao","Tristan Sylvain","Romain Laroche","Doina Precup","Yoshua Bengio"],"abstract":"Generative models can be used in planning to propose targets corresponding to states that agents deem either likely or advantageous to experience. However, imperfections, common in learned models, lead to infeasible hallucinated targets, which can cause delusional behaviors and thus safety concerns. This work first categorizes and investigates the properties of various kinds of infeasible targets. Then, we devise a strategy to reject infeasible targets with a generic target evaluator, which trains alongside planning agents as an add-on without the need to change the behavior nor the architectures of the agent (and the generative model) it is attached to. We highlight that, without proper training, the evaluator can produce delusional estimates, rendering the strategy futile. Thus, to learn correct evaluations of infeasible targets, we propose to use a combination of learning rule, architecture, and two assistive hindsight relabeling strategies. Our experiments validate significant reductions in delusional behaviors and enhancements in the performance of several kinds of existing planning agents.","url_abs":"https://arxiv.org/abs/2410.07096v7","url_pdf":"https://arxiv.org/pdf/2410.07096v7.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":"identifying-and-addressing-delusions-for","repo_url":"https://github.com/mila-iqia/delusions","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"out-of-distribution-generalization","task_name":"Out-of-Distribution Generalization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.07096","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07096"}},"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":"deterministic:regex_extraction","url":"https://github.com/mila-iqia/delusions","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":"b5fc0e5a8acc1363","entry":"bottlenecked_multi_head_attention_forward","repo":"mila-iqia/delusions","repo_kind":"official","path":"experiments/Dyna/modules.py","file_url":"https://github.com/mila-iqia/delusions/blob/HEAD/experiments/Dyna/modules.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b5fc0e5a8acc1363"}},{"code_sha256_prefix":"cbbf3a5fe2aa63f0","entry":"dijkstra","repo":"mila-iqia/delusions","repo_kind":"official","path":"experiments/Dyna/RandDistShift.py","file_url":"https://github.com/mila-iqia/delusions/blob/HEAD/experiments/Dyna/RandDistShift.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cbbf3a5fe2aa63f0"}},{"code_sha256_prefix":"7e3885e909729e31","entry":"floyd_warshall","repo":"mila-iqia/delusions","repo_kind":"official","path":"experiments/Dyna/RandDistShift.py","file_url":"https://github.com/mila-iqia/delusions/blob/HEAD/experiments/Dyna/RandDistShift.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7e3885e909729e31"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}