{"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/deep-variational-reinforcement-learning-for","title":"Deep Variational Reinforcement Learning for POMDPs","arxiv_id":"1806.02426","date":"2018-06-06","proceeding":"ICML 2018 7","authors":["Maximilian Igl","Luisa Zintgraf","Tuan Anh Le","Frank Wood","Shimon Whiteson"],"abstract":"Many real-world sequential decision making problems are partially observable\nby nature, and the environment model is typically unknown. Consequently, there\nis great need for reinforcement learning methods that can tackle such problems\ngiven only a stream of incomplete and noisy observations. In this paper, we\npropose deep variational reinforcement learning (DVRL), which introduces an\ninductive bias that allows an agent to learn a generative model of the\nenvironment and perform inference in that model to effectively aggregate the\navailable information. We develop an n-step approximation to the evidence lower\nbound (ELBO), allowing the model to be trained jointly with the policy. This\nensures that the latent state representation is suitable for the control task.\nIn experiments on Mountain Hike and flickering Atari we show that our method\noutperforms previous approaches relying on recurrent neural networks to encode\nthe past.","url_abs":"http://arxiv.org/abs/1806.02426v1","url_pdf":"http://arxiv.org/pdf/1806.02426v1.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":"deep-variational-reinforcement-learning-for","repo_url":"https://github.com/maximilianigl/DVRL","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"inductive-bias","task_name":"Inductive Bias"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"sequential-decision-making","task_name":"Sequential Decision Making"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.02426","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.02426"}},"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/maximilianigl/DVRL","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":9},"by_repo_kind":{"official":{"samples":9,"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":"8cb26dcfd6c1bb42","entry":"get_cnn_output_dimension","repo":"maximilianigl/DVRL","repo_kind":"official","path":"code/encoder_decoder.py","file_url":"https://github.com/maximilianigl/DVRL/blob/HEAD/code/encoder_decoder.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8cb26dcfd6c1bb42"}},{"code_sha256_prefix":"f9ea843ee6c0d21e","entry":"get_decoder","repo":"maximilianigl/DVRL","repo_kind":"official","path":"code/encoder_decoder.py","file_url":"https://github.com/maximilianigl/DVRL/blob/HEAD/code/encoder_decoder.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f9ea843ee6c0d21e"}},{"code_sha256_prefix":"f2c9426d0a20770c","entry":"get_encoder","repo":"maximilianigl/DVRL","repo_kind":"official","path":"code/encoder_decoder.py","file_url":"https://github.com/maximilianigl/DVRL/blob/HEAD/code/encoder_decoder.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f2c9426d0a20770c"}},{"code_sha256_prefix":"236d1803bc631286","entry":"get_environment_yaml","repo":"maximilianigl/DVRL","repo_kind":"official","path":"code/utils.py","file_url":"https://github.com/maximilianigl/DVRL/blob/HEAD/code/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"236d1803bc631286"}},{"code_sha256_prefix":"c7d3d856261b55e8","entry":"load_results","repo":"maximilianigl/DVRL","repo_kind":"official","path":"code/utils.py","file_url":"https://github.com/maximilianigl/DVRL/blob/HEAD/code/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c7d3d856261b55e8"}},{"code_sha256_prefix":"2b4c6c3104890c80","entry":"lognormexp","repo":"maximilianigl/DVRL","repo_kind":"official","path":"code/aesmc/math.py","file_url":"https://github.com/maximilianigl/DVRL/blob/HEAD/code/aesmc/math.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2b4c6c3104890c80"}},{"code_sha256_prefix":"73ebd32c9d197241","entry":"logsumexp","repo":"maximilianigl/DVRL","repo_kind":"official","path":"code/aesmc/math.py","file_url":"https://github.com/maximilianigl/DVRL/blob/HEAD/code/aesmc/math.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"73ebd32c9d197241"}},{"code_sha256_prefix":"609886a7d124e3e1","entry":"sample_ancestral_index","repo":"maximilianigl/DVRL","repo_kind":"official","path":"code/aesmc/inference.py","file_url":"https://github.com/maximilianigl/DVRL/blob/HEAD/code/aesmc/inference.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"609886a7d124e3e1"}},{"code_sha256_prefix":"ccc2f25baaaf216f","entry":"toOneHot","repo":"maximilianigl/DVRL","repo_kind":"official","path":"code/utils.py","file_url":"https://github.com/maximilianigl/DVRL/blob/HEAD/code/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ccc2f25baaaf216f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}