{"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/let-offline-rl-flow-training-conservative","title":"Let Offline RL Flow: Training Conservative Agents in the Latent Space of Normalizing Flows","arxiv_id":"2211.11096","date":"2022-11-20","proceeding":null,"authors":["Dmitriy Akimov","Vladislav Kurenkov","Alexander Nikulin","Denis Tarasov","Sergey Kolesnikov"],"abstract":"Offline reinforcement learning aims to train a policy on a pre-recorded and fixed dataset without any additional environment interactions. There are two major challenges in this setting: (1) extrapolation error caused by approximating the value of state-action pairs not well-covered by the training data and (2) distributional shift between behavior and inference policies. One way to tackle these problems is to induce conservatism - i.e., keeping the learned policies closer to the behavioral ones. To achieve this, we build upon recent works on learning policies in latent action spaces and use a special form of Normalizing Flows for constructing a generative model, which we use as a conservative action encoder. This Normalizing Flows action encoder is pre-trained in a supervised manner on the offline dataset, and then an additional policy model - controller in the latent space - is trained via reinforcement learning. This approach avoids querying actions outside of the training dataset and therefore does not require additional regularization for out-of-dataset actions. We evaluate our method on various locomotion and navigation tasks, demonstrating that our approach outperforms recently proposed algorithms with generative action models on a large portion of datasets.","url_abs":"https://arxiv.org/abs/2211.11096v2","url_pdf":"https://arxiv.org/pdf/2211.11096v2.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":"let-offline-rl-flow-training-conservative","repo_url":"https://github.com/tinkoff-ai/cnf","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"let-offline-rl-flow-training-conservative","repo_url":"https://github.com/zzmtsvv/rl_task","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"offline-rl","task_name":"Offline RL"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"normalizing-flows","method_name":"Normalizing Flows"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2211.11096","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.11096"}},"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/tinkoff-ai/cnf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zzmtsvv/rl_task","reach":null}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"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":"8ac3758971b9694b","entry":"make_optimizers","repo":"tinkoff-ai/cnf","repo_kind":"official","path":"cnf/train_rl.py","file_url":"https://github.com/tinkoff-ai/cnf/blob/HEAD/cnf/train_rl.py","link_basis":"harvester_set","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":"8ac3758971b9694b"}},{"code_sha256_prefix":"a56fcb19dade7c8e","entry":"optimize_flow","repo":"tinkoff-ai/cnf","repo_kind":"official","path":"cnf/train_flow.py","file_url":"https://github.com/tinkoff-ai/cnf/blob/HEAD/cnf/train_flow.py","link_basis":"harvester_set","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":"a56fcb19dade7c8e"}},{"code_sha256_prefix":"1310d5462c8d6dba","entry":"train_epoch","repo":"tinkoff-ai/cnf","repo_kind":"official","path":"cnf/train_flow.py","file_url":"https://github.com/tinkoff-ai/cnf/blob/HEAD/cnf/train_flow.py","link_basis":"harvester_set","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":"1310d5462c8d6dba"}},{"code_sha256_prefix":"632f8f7c106515fc","entry":"valid_batch","repo":"tinkoff-ai/cnf","repo_kind":"official","path":"cnf/train_flow.py","file_url":"https://github.com/tinkoff-ai/cnf/blob/HEAD/cnf/train_flow.py","link_basis":"harvester_set","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":"632f8f7c106515fc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}