{"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/reward-centering","title":"Reward Centering","arxiv_id":"2405.09999","date":"2024-05-16","proceeding":null,"authors":["Abhishek Naik","Yi Wan","Manan Tomar","Richard S. Sutton"],"abstract":"We show that discounted methods for solving continuing reinforcement learning problems can perform significantly better if they center their rewards by subtracting out the rewards' empirical average. The improvement is substantial at commonly used discount factors and increases further as the discount factor approaches one. In addition, we show that if a problem's rewards are shifted by a constant, then standard methods perform much worse, whereas methods with reward centering are unaffected. Estimating the average reward is straightforward in the on-policy setting; we propose a slightly more sophisticated method for the off-policy setting. Reward centering is a general idea, so we expect almost every reinforcement-learning algorithm to benefit by the addition of reward centering.","url_abs":"https://arxiv.org/abs/2405.09999v2","url_pdf":"https://arxiv.org/pdf/2405.09999v2.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":"reward-centering","repo_url":"https://github.com/abhisheknaik96/continuing-rl-exps","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"reward-centering","repo_url":"https://github.com/facebookresearch/deeprl-continuing-tasks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.09999","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.09999"}},"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/facebookresearch/deeprl-continuing-tasks","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/abhisheknaik96/continuing-rl-exps","reach":null}],"summary":{"ran_fixture":1,"unverified":8},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":8,"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":9,"samples":[{"code_sha256_prefix":"3368faa7f98435cd","entry":"process_observation","repo":"abhisheknaik96/continuing-rl-exps","repo_kind":"official","path":"experiments.py","file_url":"https://github.com/abhisheknaik96/continuing-rl-exps/blob/HEAD/experiments.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3368faa7f98435cd"}},{"code_sha256_prefix":"25eef56273d3ceb4","entry":"all_lists_same_length","repo":"facebookresearch/deeprl-continuing-tasks","repo_kind":"listed","path":"plot.py","file_url":"https://github.com/facebookresearch/deeprl-continuing-tasks/blob/HEAD/plot.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"25eef56273d3ceb4"}},{"code_sha256_prefix":"ade264405cb0c63c","entry":"generate_latex_table","repo":"facebookresearch/deeprl-continuing-tasks","repo_kind":"listed","path":"experiments/predefined_resets_atari/latex_table_continuing_episodic_comparison.py","file_url":"https://github.com/facebookresearch/deeprl-continuing-tasks/blob/HEAD/experiments/predefined_resets_atari/latex_table_continuing_episodic_comparison.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"ade264405cb0c63c"}},{"code_sha256_prefix":"251b1b37661e581d","entry":"generate_latex_table","repo":"facebookresearch/deeprl-continuing-tasks","repo_kind":"listed","path":"experiments/predefined_resets_mujoco/latex_table_continuing_episodic_comparison.py","file_url":"https://github.com/facebookresearch/deeprl-continuing-tasks/blob/HEAD/experiments/predefined_resets_mujoco/latex_table_continuing_episodic_comparison.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"251b1b37661e581d"}},{"code_sha256_prefix":"c1496d1d3abc80c1","entry":"generate_latex_table","repo":"facebookresearch/deeprl-continuing-tasks","repo_kind":"listed","path":"experiments/agent_resets_mujoco/latex_table_agent_controlled_predefined_comparison.py","file_url":"https://github.com/facebookresearch/deeprl-continuing-tasks/blob/HEAD/experiments/agent_resets_mujoco/latex_table_agent_controlled_predefined_comparison.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"c1496d1d3abc80c1"}},{"code_sha256_prefix":"381a448726054575","entry":"generate_latex_table","repo":"facebookresearch/deeprl-continuing-tasks","repo_kind":"listed","path":"experiments/no_resets_mujoco/latex_table_reduced_state_space_improvement_table.py","file_url":"https://github.com/facebookresearch/deeprl-continuing-tasks/blob/HEAD/experiments/no_resets_mujoco/latex_table_reduced_state_space_improvement_table.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"381a448726054575"}},{"code_sha256_prefix":"3141235c6a905d44","entry":"generate_latex_table","repo":"facebookresearch/deeprl-continuing-tasks","repo_kind":"listed","path":"experiments/no_resets_mujoco/latex_table_resets_improvement_table.py","file_url":"https://github.com/facebookresearch/deeprl-continuing-tasks/blob/HEAD/experiments/no_resets_mujoco/latex_table_resets_improvement_table.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"3141235c6a905d44"}},{"code_sha256_prefix":"1fb4d27e51476ca3","entry":"get_stats_learning_curves_to_print","repo":"facebookresearch/deeprl-continuing-tasks","repo_kind":"listed","path":"plot.py","file_url":"https://github.com/facebookresearch/deeprl-continuing-tasks/blob/HEAD/plot.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"1fb4d27e51476ca3"}},{"code_sha256_prefix":"e0c392b58c103644","entry":"stats_significant","repo":"facebookresearch/deeprl-continuing-tasks","repo_kind":"listed","path":"experiments/predefined_resets_atari/latex_table_continuing_episodic_comparison.py","file_url":"https://github.com/facebookresearch/deeprl-continuing-tasks/blob/HEAD/experiments/predefined_resets_atari/latex_table_continuing_episodic_comparison.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"e0c392b58c103644"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}