{"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/data-efficient-reinforcement-learning-with-1","title":"Data-Efficient Reinforcement Learning with Self-Predictive Representations","arxiv_id":"2007.05929","date":"2020-07-12","proceeding":"ICLR 2021 1","authors":["Max Schwarzer","Ankesh Anand","Rishab Goel","R. Devon Hjelm","Aaron Courville","Philip Bachman"],"abstract":"While deep reinforcement learning excels at solving tasks where large amounts of data can be collected through virtually unlimited interaction with the environment, learning from limited interaction remains a key challenge. We posit that an agent can learn more efficiently if we augment reward maximization with self-supervised objectives based on structure in its visual input and sequential interaction with the environment. Our method, Self-Predictive Representations(SPR), trains an agent to predict its own latent state representations multiple steps into the future. We compute target representations for future states using an encoder which is an exponential moving average of the agent's parameters and we make predictions using a learned transition model. On its own, this future prediction objective outperforms prior methods for sample-efficient deep RL from pixels. We further improve performance by adding data augmentation to the future prediction loss, which forces the agent's representations to be consistent across multiple views of an observation. Our full self-supervised objective, which combines future prediction and data augmentation, achieves a median human-normalized score of 0.415 on Atari in a setting limited to 100k steps of environment interaction, which represents a 55% relative improvement over the previous state-of-the-art. Notably, even in this limited data regime, SPR exceeds expert human scores on 7 out of 26 games. The code associated with this work is available at https://github.com/mila-iqia/spr","url_abs":"https://arxiv.org/abs/2007.05929v4","url_pdf":"https://arxiv.org/pdf/2007.05929v4.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":"data-efficient-reinforcement-learning-with-1","repo_url":"https://github.com/mila-iqia/spr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"atari-games-100k","task_name":"Atari Games 100k"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"future-prediction","task_name":"Future prediction"},{"task_slug":"general-reinforcement-learning","task_name":"General Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2007.05929","atlas_url":"https://app.syntology.ai/?focus=2007.05929","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.05929"}},"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/mila-iqia/spr","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":1,"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":"33a582f5c65e69d0","entry":"calculate_accuracy","repo":"mila-iqia/spr","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/mila-iqia/spr/blob/HEAD/src/utils.py","link_basis":"plan_row","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":"33a582f5c65e69d0"}},{"code_sha256_prefix":"01ea1c18cea4f892","entry":"fig2data","repo":"mila-iqia/spr","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/mila-iqia/spr/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"01ea1c18cea4f892"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}