{"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/deep-q-network-with-proximal-iteration-1","title":"Faster Deep Reinforcement Learning with Slower Online Network","arxiv_id":"2112.05848","date":"2021-12-10","proceeding":null,"authors":["Kavosh Asadi","Rasool Fakoor","Omer Gottesman","Taesup Kim","Michael L. Littman","Alexander J. Smola"],"abstract":"Deep reinforcement learning algorithms often use two networks for value function optimization: an online network, and a target network that tracks the online network with some delay. Using two separate networks enables the agent to hedge against issues that arise when performing bootstrapping. In this paper we endow two popular deep reinforcement learning algorithms, namely DQN and Rainbow, with updates that incentivize the online network to remain in the proximity of the target network. This improves the robustness of deep reinforcement learning in presence of noisy updates. The resultant agents, called DQN Pro and Rainbow Pro, exhibit significant performance improvements over their original counterparts on the Atari benchmark demonstrating the effectiveness of this simple idea in deep reinforcement learning. The code for our paper is available here: Github.com/amazon-research/fast-rl-with-slow-updates.","url_abs":"https://arxiv.org/abs/2112.05848v3","url_pdf":"https://arxiv.org/pdf/2112.05848v3.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":"deep-q-network-with-proximal-iteration-1","repo_url":"https://github.com/amazon-research/fast-rl-with-slow-updates","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement 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":"convolution","method_name":"Convolution"},{"method_slug":"dqn","method_name":"DQN"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"q-learning","method_name":"Q-Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2112.05848","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.05848"}},"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":"deterministic:regex_extraction","url":"https://github.com/amazon-research/fast-rl-with-slow-updates","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":9},"by_repo_kind":{"official":{"samples":9,"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":0,"samples":[{"code_sha256_prefix":"9452ab3fdaceeaf7","entry":"get_latest_file","repo":"amazon-research/fast-rl-with-slow-updates","repo_kind":"official","path":"dopamine/colab/utils.py","file_url":"https://github.com/amazon-research/fast-rl-with-slow-updates/blob/HEAD/dopamine/colab/utils.py","link_basis":"harvester_set","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":"9452ab3fdaceeaf7"}},{"code_sha256_prefix":"af103360bcc90e53","entry":"huber_loss","repo":"amazon-research/fast-rl-with-slow-updates","repo_kind":"official","path":"dopamine/jax/losses.py","file_url":"https://github.com/amazon-research/fast-rl-with-slow-updates/blob/HEAD/dopamine/jax/losses.py","link_basis":"harvester_set","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":"af103360bcc90e53"}},{"code_sha256_prefix":"ba90a401fa9b20dc","entry":"load_baselines","repo":"amazon-research/fast-rl-with-slow-updates","repo_kind":"official","path":"dopamine/colab/utils.py","file_url":"https://github.com/amazon-research/fast-rl-with-slow-updates/blob/HEAD/dopamine/colab/utils.py","link_basis":"harvester_set","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":"ba90a401fa9b20dc"}},{"code_sha256_prefix":"9695996bed46d48b","entry":"load_rewards","repo":"amazon-research/fast-rl-with-slow-updates","repo_kind":"official","path":"extract_reward.py","file_url":"https://github.com/amazon-research/fast-rl-with-slow-updates/blob/HEAD/extract_reward.py","link_basis":"harvester_set","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":"9695996bed46d48b"}},{"code_sha256_prefix":"00989d2027cbd4f1","entry":"load_statistics","repo":"amazon-research/fast-rl-with-slow-updates","repo_kind":"official","path":"dopamine/colab/utils.py","file_url":"https://github.com/amazon-research/fast-rl-with-slow-updates/blob/HEAD/dopamine/colab/utils.py","link_basis":"harvester_set","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":"00989d2027cbd4f1"}},{"code_sha256_prefix":"1c9e08f4b6f3cca7","entry":"mse_loss","repo":"amazon-research/fast-rl-with-slow-updates","repo_kind":"official","path":"dopamine/jax/losses.py","file_url":"https://github.com/amazon-research/fast-rl-with-slow-updates/blob/HEAD/dopamine/jax/losses.py","link_basis":"harvester_set","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":"1c9e08f4b6f3cca7"}},{"code_sha256_prefix":"922cb4050cda4895","entry":"preprocess_atari_inputs","repo":"amazon-research/fast-rl-with-slow-updates","repo_kind":"official","path":"dopamine/jax/networks.py","file_url":"https://github.com/amazon-research/fast-rl-with-slow-updates/blob/HEAD/dopamine/jax/networks.py","link_basis":"harvester_set","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":"922cb4050cda4895"}},{"code_sha256_prefix":"ef22b2a24e026064","entry":"smooth","repo":"amazon-research/fast-rl-with-slow-updates","repo_kind":"official","path":"extract_reward.py","file_url":"https://github.com/amazon-research/fast-rl-with-slow-updates/blob/HEAD/extract_reward.py","link_basis":"harvester_set","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":"ef22b2a24e026064"}},{"code_sha256_prefix":"5fb03fa44bd6c56a","entry":"softmax_cross_entropy_loss_with_logits","repo":"amazon-research/fast-rl-with-slow-updates","repo_kind":"official","path":"dopamine/jax/losses.py","file_url":"https://github.com/amazon-research/fast-rl-with-slow-updates/blob/HEAD/dopamine/jax/losses.py","link_basis":"harvester_set","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":"5fb03fa44bd6c56a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}