{"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/diffusion-policies-as-an-expressive-policy","title":"Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning","arxiv_id":"2208.06193","date":"2022-08-12","proceeding":null,"authors":["Zhendong Wang","Jonathan J Hunt","Mingyuan Zhou"],"abstract":"Offline reinforcement learning (RL), which aims to learn an optimal policy using a previously collected static dataset, is an important paradigm of RL. Standard RL methods often perform poorly in this regime due to the function approximation errors on out-of-distribution actions. While a variety of regularization methods have been proposed to mitigate this issue, they are often constrained by policy classes with limited expressiveness that can lead to highly suboptimal solutions. In this paper, we propose representing the policy as a diffusion model, a recent class of highly-expressive deep generative models. We introduce Diffusion Q-learning (Diffusion-QL) that utilizes a conditional diffusion model to represent the policy. In our approach, we learn an action-value function and we add a term maximizing action-values into the training loss of the conditional diffusion model, which results in a loss that seeks optimal actions that are near the behavior policy. We show the expressiveness of the diffusion model-based policy, and the coupling of the behavior cloning and policy improvement under the diffusion model both contribute to the outstanding performance of Diffusion-QL. We illustrate the superiority of our method compared to prior works in a simple 2D bandit example with a multimodal behavior policy. We then show that our method can achieve state-of-the-art performance on the majority of the D4RL benchmark tasks.","url_abs":"https://arxiv.org/abs/2208.06193v3","url_pdf":"https://arxiv.org/pdf/2208.06193v3.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":"diffusion-policies-as-an-expressive-policy","repo_url":"https://github.com/zhendong-wang/diffusion-policies-for-offline-rl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"diffusion-policies-as-an-expressive-policy","repo_url":"https://github.com/quantumiracle/consistency_model_for_reinforcement_learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"diffusion-policies-as-an-expressive-policy","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":"d4rl","task_name":"D4RL"},{"task_slug":"offline-rl","task_name":"Offline RL"},{"task_slug":"q-learning","task_name":"Q-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"},{"method_slug":"q-learning","method_name":"Q-Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2208.06193","atlas_url":"https://app.syntology.ai/?focus=2208.06193","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.06193"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/zhendong-wang/diffusion-policies-for-offline-rl","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zzmtsvv/rl_task","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/quantumiracle/consistency_model_for_reinforcement_learning","reach":null}],"summary":{"ran":10,"ran_honours":1,"unverified":7},"by_repo_kind":{"official":{"samples":3,"ran":1,"repositories":1},"listed":{"samples":15,"ran":10,"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":10,"samples":[{"code_sha256_prefix":"08e51c2d2c41c81f","entry":"DDPM","repo":"zzmtsvv/rl_task","repo_kind":"listed","path":"diffusion_ql/dql.py","file_url":"https://github.com/zzmtsvv/rl_task/blob/HEAD/diffusion_ql/dql.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"08e51c2d2c41c81f"}},{"code_sha256_prefix":"cb039993bd16f94c","entry":"EMA","repo":"zhendong-wang/diffusion-policies-for-offline-rl","repo_kind":"official","path":"agents/ql_diffusion.py","file_url":"https://github.com/zhendong-wang/diffusion-policies-for-offline-rl/blob/HEAD/agents/ql_diffusion.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cb039993bd16f94c"}},{"code_sha256_prefix":"19732228c46fa1ba","entry":"EMA","repo":"quantumiracle/consistency_model_for_reinforcement_learning","repo_kind":"listed","path":"agents/ql_diffusion.py","file_url":"https://github.com/quantumiracle/consistency_model_for_reinforcement_learning/blob/HEAD/agents/ql_diffusion.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"19732228c46fa1ba"}},{"code_sha256_prefix":"d6fcbdadf8cb4e3f","entry":"EnsembledCritic","repo":"zzmtsvv/rl_task","repo_kind":"listed","path":"diffusion_ql/dql.py","file_url":"https://github.com/zzmtsvv/rl_task/blob/HEAD/diffusion_ql/dql.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":"d6fcbdadf8cb4e3f"}},{"code_sha256_prefix":"ac150cae89f0e687","entry":"EnsembledLinear","repo":"zzmtsvv/rl_task","repo_kind":"listed","path":"diffusion_ql/dql.py","file_url":"https://github.com/zzmtsvv/rl_task/blob/HEAD/diffusion_ql/dql.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":"ac150cae89f0e687"}},{"code_sha256_prefix":"911033f1c5373d15","entry":"MLP","repo":"zzmtsvv/rl_task","repo_kind":"listed","path":"diffusion_ql/dql.py","file_url":"https://github.com/zzmtsvv/rl_task/blob/HEAD/diffusion_ql/dql.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"911033f1c5373d15"}},{"code_sha256_prefix":"6a06af32e9295cda","entry":"MLP","repo":"quantumiracle/consistency_model_for_reinforcement_learning","repo_kind":"listed","path":"agents/ql_diffusion.py","file_url":"https://github.com/quantumiracle/consistency_model_for_reinforcement_learning/blob/HEAD/agents/ql_diffusion.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6a06af32e9295cda"}},{"code_sha256_prefix":"ef90a18431b489f9","entry":"PositionalEncoding","repo":"zzmtsvv/rl_task","repo_kind":"listed","path":"diffusion_ql/dql.py","file_url":"https://github.com/zzmtsvv/rl_task/blob/HEAD/diffusion_ql/dql.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":"ef90a18431b489f9"}},{"code_sha256_prefix":"480e0c2c2219727e","entry":"WeightedL2","repo":"zzmtsvv/rl_task","repo_kind":"listed","path":"diffusion_ql/dql.py","file_url":"https://github.com/zzmtsvv/rl_task/blob/HEAD/diffusion_ql/dql.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"480e0c2c2219727e"}},{"code_sha256_prefix":"9cbe616246577b15","entry":"dql_config","repo":"zzmtsvv/rl_task","repo_kind":"listed","path":"diffusion_ql/dql.py","file_url":"https://github.com/zzmtsvv/rl_task/blob/HEAD/diffusion_ql/dql.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":"9cbe616246577b15"}},{"code_sha256_prefix":"25a711883c5a59fe","entry":"vp_beta_schedule","repo":"zzmtsvv/rl_task","repo_kind":"listed","path":"diffusion_ql/dql.py","file_url":"https://github.com/zzmtsvv/rl_task/blob/HEAD/diffusion_ql/dql.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"25a711883c5a59fe"}},{"code_sha256_prefix":"a8e86dce13aa99a1","entry":"Diffusion","repo":"zhendong-wang/diffusion-policies-for-offline-rl","repo_kind":"official","path":"agents/ql_diffusion.py","file_url":"https://github.com/zhendong-wang/diffusion-policies-for-offline-rl/blob/HEAD/agents/ql_diffusion.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":"a8e86dce13aa99a1"}},{"code_sha256_prefix":"49c674376f6d739f","entry":"Diffusion","repo":"quantumiracle/consistency_model_for_reinforcement_learning","repo_kind":"listed","path":"agents/ql_diffusion.py","file_url":"https://github.com/quantumiracle/consistency_model_for_reinforcement_learning/blob/HEAD/agents/ql_diffusion.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":"49c674376f6d739f"}},{"code_sha256_prefix":"8136ea50760183ad","entry":"DiffusionQL","repo":"zzmtsvv/rl_task","repo_kind":"listed","path":"diffusion_ql/dql.py","file_url":"https://github.com/zzmtsvv/rl_task/blob/HEAD/diffusion_ql/dql.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":"8136ea50760183ad"}},{"code_sha256_prefix":"56d3224268de9651","entry":"Diffusion_QL","repo":"zhendong-wang/diffusion-policies-for-offline-rl","repo_kind":"official","path":"agents/ql_diffusion.py","file_url":"https://github.com/zhendong-wang/diffusion-policies-for-offline-rl/blob/HEAD/agents/ql_diffusion.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":"56d3224268de9651"}},{"code_sha256_prefix":"f3e8db467ebcdc65","entry":"Diffusion_QL","repo":"quantumiracle/consistency_model_for_reinforcement_learning","repo_kind":"listed","path":"agents/ql_diffusion.py","file_url":"https://github.com/quantumiracle/consistency_model_for_reinforcement_learning/blob/HEAD/agents/ql_diffusion.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":"f3e8db467ebcdc65"}},{"code_sha256_prefix":"a193aa42d45269f9","entry":"WeightedHuber","repo":"quantumiracle/consistency_model_for_reinforcement_learning","repo_kind":"listed","path":"agents/ql_diffusion.py","file_url":"https://github.com/quantumiracle/consistency_model_for_reinforcement_learning/blob/HEAD/agents/ql_diffusion.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":"a193aa42d45269f9"}},{"code_sha256_prefix":"ba56ef20ff6743ce","entry":"extract","repo":"zzmtsvv/rl_task","repo_kind":"listed","path":"diffusion_ql/dql.py","file_url":"https://github.com/zzmtsvv/rl_task/blob/HEAD/diffusion_ql/dql.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":"ba56ef20ff6743ce"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}