{"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/reasoning-with-latent-diffusion-in-offline","title":"Reasoning with Latent Diffusion in Offline Reinforcement Learning","arxiv_id":"2309.06599","date":"2023-09-12","proceeding":null,"authors":["Siddarth Venkatraman","Shivesh Khaitan","Ravi Tej Akella","John Dolan","Jeff Schneider","Glen Berseth"],"abstract":"Offline reinforcement learning (RL) holds promise as a means to learn high-reward policies from a static dataset, without the need for further environment interactions. However, a key challenge in offline RL lies in effectively stitching portions of suboptimal trajectories from the static dataset while avoiding extrapolation errors arising due to a lack of support in the dataset. Existing approaches use conservative methods that are tricky to tune and struggle with multi-modal data (as we show) or rely on noisy Monte Carlo return-to-go samples for reward conditioning. In this work, we propose a novel approach that leverages the expressiveness of latent diffusion to model in-support trajectory sequences as compressed latent skills. This facilitates learning a Q-function while avoiding extrapolation error via batch-constraining. The latent space is also expressive and gracefully copes with multi-modal data. We show that the learned temporally-abstract latent space encodes richer task-specific information for offline RL tasks as compared to raw state-actions. This improves credit assignment and facilitates faster reward propagation during Q-learning. Our method demonstrates state-of-the-art performance on the D4RL benchmarks, particularly excelling in long-horizon, sparse-reward tasks.","url_abs":"https://arxiv.org/abs/2309.06599v1","url_pdf":"https://arxiv.org/pdf/2309.06599v1.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":"reasoning-with-latent-diffusion-in-offline","repo_url":"https://github.com/ldcq/ldcq","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"d4rl","task_name":"D4RL"},{"task_slug":"offline-rl","task_name":"Offline RL"},{"task_slug":"q-learning","task_name":"Q-Learning"},{"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":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2309.06599","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.06599"}},"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/ldcq/ldcq","reach":{"status":"ok"}}],"summary":{"ran":4,"unverified":2},"by_repo_kind":{"official":{"samples":6,"ran":4,"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":6,"samples":[{"code_sha256_prefix":"72d8b48972f1b220","entry":"ddpm_schedules","repo":"ldcq/ldcq","repo_kind":"official","path":"models/diffusion_models.py","file_url":"https://github.com/ldcq/ldcq/blob/HEAD/models/diffusion_models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"72d8b48972f1b220"}},{"code_sha256_prefix":"1f005f78dfb64e39","entry":"diffusion_prior_policy","repo":"ldcq/ldcq","repo_kind":"official","path":"eval/plan_skills_diffusion_franka.py","file_url":"https://github.com/ldcq/ldcq/blob/HEAD/eval/plan_skills_diffusion_franka.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1f005f78dfb64e39"}},{"code_sha256_prefix":"16821d17ba2a94f5","entry":"prior_policy","repo":"ldcq/ldcq","repo_kind":"official","path":"eval/plan_skills_diffusion.py","file_url":"https://github.com/ldcq/ldcq/blob/HEAD/eval/plan_skills_diffusion.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"16821d17ba2a94f5"}},{"code_sha256_prefix":"eb9e80fb4381d4fe","entry":"prior_policy","repo":"ldcq/ldcq","repo_kind":"official","path":"eval/plan_skills_diffusion_franka.py","file_url":"https://github.com/ldcq/ldcq/blob/HEAD/eval/plan_skills_diffusion_franka.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"eb9e80fb4381d4fe"}},{"code_sha256_prefix":"4499324763e1dd19","entry":"diffusion_prior_policy","repo":"ldcq/ldcq","repo_kind":"official","path":"eval/plan_skills_diffusion.py","file_url":"https://github.com/ldcq/ldcq/blob/HEAD/eval/plan_skills_diffusion.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4499324763e1dd19"}},{"code_sha256_prefix":"23ad53f7e3f42326","entry":"q_policy","repo":"ldcq/ldcq","repo_kind":"official","path":"diffusion1d/eval_random_walk.py","file_url":"https://github.com/ldcq/ldcq/blob/HEAD/diffusion1d/eval_random_walk.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"23ad53f7e3f42326"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}