{"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/learning-to-act-by-predicting-the-future","title":"Learning to Act by Predicting the Future","arxiv_id":"1611.01779","date":"2016-11-06","proceeding":null,"authors":["Alexey Dosovitskiy","Vladlen Koltun"],"abstract":"We present an approach to sensorimotor control in immersive environments. Our\napproach utilizes a high-dimensional sensory stream and a lower-dimensional\nmeasurement stream. The cotemporal structure of these streams provides a rich\nsupervisory signal, which enables training a sensorimotor control model by\ninteracting with the environment. The model is trained using supervised\nlearning techniques, but without extraneous supervision. It learns to act based\non raw sensory input from a complex three-dimensional environment. The\npresented formulation enables learning without a fixed goal at training time,\nand pursuing dynamically changing goals at test time. We conduct extensive\nexperiments in three-dimensional simulations based on the classical\nfirst-person game Doom. The results demonstrate that the presented approach\noutperforms sophisticated prior formulations, particularly on challenging\ntasks. The results also show that trained models successfully generalize across\nenvironments and goals. A model trained using the presented approach won the\nFull Deathmatch track of the Visual Doom AI Competition, which was held in\npreviously unseen environments.","url_abs":"http://arxiv.org/abs/1611.01779v2","url_pdf":"http://arxiv.org/pdf/1611.01779v2.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":"learning-to-act-by-predicting-the-future","repo_url":"https://github.com/a-mcego/DirectFuturePred_tf2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"learning-to-act-by-predicting-the-future","repo_url":"https://github.com/flyyufelix/Direct-Future-Prediction-Keras","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1611.01779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.01779"}},"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/flyyufelix/Direct-Future-Prediction-Keras","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/a-mcego/DirectFuturePred_tf2","reach":null}],"summary":{"ran_honours":2,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"listed":{"samples":4,"ran":3,"repositories":2}},"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":3,"samples":[{"code_sha256_prefix":"eb26ab9516fb495d","entry":"get_damagecount","repo":"a-mcego/DirectFuturePred_tf2","repo_kind":"listed","path":"DFP_helpers.py","file_url":"https://github.com/a-mcego/DirectFuturePred_tf2/blob/HEAD/DFP_helpers.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"eb26ab9516fb495d"}},{"code_sha256_prefix":"b5e50f073420f59b","entry":"get_deadness","repo":"a-mcego/DirectFuturePred_tf2","repo_kind":"listed","path":"DFP_helpers.py","file_url":"https://github.com/a-mcego/DirectFuturePred_tf2/blob/HEAD/DFP_helpers.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"b5e50f073420f59b"}},{"code_sha256_prefix":"42acde6d218c4d3b","entry":"get_nth_var","repo":"a-mcego/DirectFuturePred_tf2","repo_kind":"listed","path":"DFP_helpers.py","file_url":"https://github.com/a-mcego/DirectFuturePred_tf2/blob/HEAD/DFP_helpers.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"42acde6d218c4d3b"}},{"code_sha256_prefix":"86d7f1904528d8a5","entry":"preprocessImg","repo":"flyyufelix/Direct-Future-Prediction-Keras","repo_kind":"listed","path":"dfp.py","file_url":"https://github.com/flyyufelix/Direct-Future-Prediction-Keras/blob/HEAD/dfp.py","link_basis":"harvester_set","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":"86d7f1904528d8a5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}