{"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/experience-replay-with-likelihood-free","title":"Experience Replay with Likelihood-free Importance Weights","arxiv_id":"2006.13169","date":"2020-06-23","proceeding":null,"authors":["Samarth Sinha","Jiaming Song","Animesh Garg","Stefano Ermon"],"abstract":"The use of past experiences to accelerate temporal difference (TD) learning of value functions, or experience replay, is a key component in deep reinforcement learning. Prioritization or reweighting of important experiences has shown to improve performance of TD learning algorithms.In this work, we propose to reweight experiences based on their likelihood under the stationary distribution of the current policy. Using the corresponding reweighted TD objective, we implicitly encourage small approximation errors on the value function over frequently encountered states. We use a likelihood-free density ratio estimator over the replay buffer to assign the prioritization weights. We apply the proposed approach empirically on two competitive methods, Soft Actor Critic (SAC) and Twin Delayed Deep Deterministic policy gradient (TD3) -- over a suite of OpenAI gym tasks and achieve superior sample complexity compared to other baseline approaches.","url_abs":"https://arxiv.org/abs/2006.13169v1","url_pdf":"https://arxiv.org/pdf/2006.13169v1.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":"experience-replay-with-likelihood-free","repo_url":"https://github.com/AIDefender/MyDiscor","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"openai-gym","task_name":"OpenAI Gym"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"experience-replay","method_name":"Experience Replay"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"soft-actor-critic","method_name":"Soft Actor Critic"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2006.13169","atlas_url":"https://app.syntology.ai/?focus=2006.13169","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.13169"}},"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/AIDefender/MyDiscor","reach":null}],"summary":{"ran_honours":2},"by_repo_kind":{"listed":{"samples":2,"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":0,"samples":[{"code_sha256_prefix":"310c696192de629c","entry":"kl_divergence","repo":"AIDefender/MyDiscor","repo_kind":"listed","path":"discor/algorithm/rlkit/torch/iwq/iwq.py","file_url":"https://github.com/AIDefender/MyDiscor/blob/HEAD/discor/algorithm/rlkit/torch/iwq/iwq.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"310c696192de629c"}},{"code_sha256_prefix":"362aea1c56de9240","entry":"weighted_mse_loss","repo":"AIDefender/MyDiscor","repo_kind":"listed","path":"discor/algorithm/rlkit/torch/iwq/iwq.py","file_url":"https://github.com/AIDefender/MyDiscor/blob/HEAD/discor/algorithm/rlkit/torch/iwq/iwq.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"362aea1c56de9240"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}