{"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/off-policy-average-reward-actor-critic-with","title":"Off-Policy Average Reward Actor-Critic with Deterministic Policy Search","arxiv_id":"2305.12239","date":"2023-05-20","proceeding":null,"authors":["Naman Saxena","Subhojyoti Khastigir","Shishir Kolathaya","Shalabh Bhatnagar"],"abstract":"The average reward criterion is relatively less studied as most existing works in the Reinforcement Learning literature consider the discounted reward criterion. There are few recent works that present on-policy average reward actor-critic algorithms, but average reward off-policy actor-critic is relatively less explored. In this work, we present both on-policy and off-policy deterministic policy gradient theorems for the average reward performance criterion. Using these theorems, we also present an Average Reward Off-Policy Deep Deterministic Policy Gradient (ARO-DDPG) Algorithm. We first show asymptotic convergence analysis using the ODE-based method. Subsequently, we provide a finite time analysis of the resulting stochastic approximation scheme with linear function approximator and obtain an $\\epsilon$-optimal stationary policy with a sample complexity of $\\Omega(\\epsilon^{-2.5})$. We compare the average reward performance of our proposed ARO-DDPG algorithm and observe better empirical performance compared to state-of-the-art on-policy average reward actor-critic algorithms over MuJoCo-based environments.","url_abs":"https://arxiv.org/abs/2305.12239v2","url_pdf":"https://arxiv.org/pdf/2305.12239v2.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":"off-policy-average-reward-actor-critic-with","repo_url":"https://github.com/yhisaki/average-reward-drl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"mujoco","task_name":"MuJoCo"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2305.12239","atlas_url":"https://app.syntology.ai/?focus=2305.12239","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.12239"}},"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":"deterministic:regex_extraction","url":"https://github.com/namansaxena9/ARO-DDPG","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yhisaki/average-reward-drl","reach":null}],"summary":{"ran":3,"unverified":3},"by_repo_kind":{"listed":{"samples":2,"ran":1,"repositories":1},"found_in_text":{"samples":4,"ran":2,"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":"8dc8b64c468580f4","entry":"Actor","repo":"namansaxena9/ARO-DDPG","repo_kind":"found_in_text","path":"cheetah_run/ddpg_model.py","file_url":"https://github.com/namansaxena9/ARO-DDPG/blob/HEAD/cheetah_run/ddpg_model.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":"8dc8b64c468580f4"}},{"code_sha256_prefix":"54a47607104f9c47","entry":"Logger","repo":"namansaxena9/ARO-DDPG","repo_kind":"found_in_text","path":"cheetah_run/ddpg_model.py","file_url":"https://github.com/namansaxena9/ARO-DDPG/blob/HEAD/cheetah_run/ddpg_model.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":"54a47607104f9c47"}},{"code_sha256_prefix":"1e3101a1ad8f1b30","entry":"OUNoise","repo":"yhisaki/average-reward-drl","repo_kind":"listed","path":"average_reward_drl/algorithms/aro_ddpg.py","file_url":"https://github.com/yhisaki/average-reward-drl/blob/HEAD/average_reward_drl/algorithms/aro_ddpg.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":"1e3101a1ad8f1b30"}},{"code_sha256_prefix":"d21ac2a224a9ba3e","entry":"ARO_DDPG","repo":"yhisaki/average-reward-drl","repo_kind":"listed","path":"average_reward_drl/algorithms/aro_ddpg.py","file_url":"https://github.com/yhisaki/average-reward-drl/blob/HEAD/average_reward_drl/algorithms/aro_ddpg.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":"d21ac2a224a9ba3e"}},{"code_sha256_prefix":"18aff75275d837d5","entry":"Agent","repo":"namansaxena9/ARO-DDPG","repo_kind":"found_in_text","path":"cheetah_run/ddpg_model.py","file_url":"https://github.com/namansaxena9/ARO-DDPG/blob/HEAD/cheetah_run/ddpg_model.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":"18aff75275d837d5"}},{"code_sha256_prefix":"e114b8f10c6d0466","entry":"Critic","repo":"namansaxena9/ARO-DDPG","repo_kind":"found_in_text","path":"cheetah_run/ddpg_model.py","file_url":"https://github.com/namansaxena9/ARO-DDPG/blob/HEAD/cheetah_run/ddpg_model.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":"e114b8f10c6d0466"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}