{"url":"/task/transfer-reinforcement-learning","name":"Transfer Reinforcement Learning","slug":"transfer-reinforcement-learning","description_markdown":null,"categories":[{"name":"Methodology","url":"/area/methodology"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":41,"papers_with_code":14,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[{"url":"/dataset/bipedal-skills","name":"bipedal-skills","full_name":"Bipedal Skills Benchmark for Reinforcement Learning","num_papers_in_archive":2}],"subtasks":[],"parent_tasks":[{"url":"/task/transfer-learning","name":"Transfer Learning"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":14,"of":14,"tagged_in_all":41,"items":[{"url":"/paper/actor-mimic-deep-multitask-and-transfer","title":"Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning","date":"2015-11-19","arxiv_id":"1511.06342","repositories_listed":3,"syntology":null},{"url":"/paper/multipolar-multi-source-policy-aggregation","title":"MULTIPOLAR: Multi-Source Policy Aggregation for Transfer Reinforcement Learning between Diverse Environmental Dynamics","date":"2019-09-28","arxiv_id":"1909.13111","repositories_listed":2,"syntology":null},{"url":"/paper/vusfavariational-universal-successor-features","title":"VUSFA:Variational Universal Successor Features Approximator to Improve Transfer DRL for Target Driven Visual Navigation","date":"2019-08-18","arxiv_id":"1908.06376","repositories_listed":2,"syntology":null},{"url":"/paper/hybrid-transfer-reinforcement-learning","title":"Hybrid Transfer Reinforcement Learning: Provable Sample Efficiency from Shifted-Dynamics Data","date":"2024-11-06","arxiv_id":"2411.03810","repositories_listed":1,"syntology":null},{"url":"/paper/transfer-reinforcement-learning-for-differing","title":"Transfer Reinforcement Learning for Differing Action Spaces via Q-Network Representations","date":"2022-02-05","arxiv_id":"2202.02442","repositories_listed":1,"syntology":null},{"url":"/paper/adarl-what-where-and-how-to-adapt-in-transfer","title":"AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning","date":"2021-07-06","arxiv_id":"2107.02729","repositories_listed":1,"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/scalable-multiagent-driving-policies-for","title":"Scalable Multiagent Driving Policies For Reducing Traffic Congestion","date":"2021-02-26","arxiv_id":"2103.00058","repositories_listed":1,"syntology":null},{"url":"/paper/domain-adaptation-in-reinforcement-learning","title":"Domain Adaptation In Reinforcement Learning Via Latent Unified State Representation","date":"2021-02-10","arxiv_id":"2102.05714","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":4}},{"url":"/paper/action-priors-for-large-action-spaces-in","title":"Action Priors for Large Action Spaces in Robotics","date":"2021-01-11","arxiv_id":"2101.04178","repositories_listed":1,"syntology":null},{"url":"/paper/gym-gazebo2-a-toolkit-for-reinforcement","title":"gym-gazebo2, a toolkit for reinforcement learning using ROS 2 and Gazebo","date":"2019-03-14","arxiv_id":"1903.06278","repositories_listed":1,"syntology":null},{"url":"/paper/hardware-conditioned-policies-for-multi-robot","title":"Hardware Conditioned Policies for Multi-Robot Transfer Learning","date":"2018-11-24","arxiv_id":"1811.09864","repositories_listed":1,"syntology":null},{"url":"/paper/deep-transfer-reinforcement-learning-for-text","title":"Deep Transfer Reinforcement Learning for Text Summarization","date":"2018-10-15","arxiv_id":"1810.06667","repositories_listed":1,"syntology":null},{"url":"/paper/universal-planning-networks","title":"Universal Planning Networks","date":"2018-04-02","arxiv_id":"1804.00645","repositories_listed":1,"syntology":null},{"url":"/paper/shapechanger-environments-for-transfer","title":"Shapechanger: Environments for Transfer Learning","date":"2017-09-15","arxiv_id":"1709.05070","repositories_listed":1,"syntology":null}],"syntology_records":2,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}