{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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 (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":41,"of":41,"of_with_code":14,"tagged_in_all":41,"counts":{"archive_papers_tagged":41,"with_a_code_link":14,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":41,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":2,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/actor-mimic-deep-multitask-and-transfer","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/adarl-what-where-and-how-to-adapt-in-transfer#ran","syntology_url":"https://syntology.ai/paper/2107.02729","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.02729"}},"official":{"repos":["adaptive-rl/adarl-code"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/scalable-multiagent-driving-policies-for","slug":"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","slug":"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_constructed":3,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"4 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/domain-adaptation-in-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2102.05714","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.05714"}},"official":{"repos":["KarlXing/LUSR"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/action-priors-for-large-action-spaces-in","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"shapechanger-environments-for-transfer","title":"Shapechanger: Environments for Transfer Learning","date":"2017-09-15","arxiv_id":"1709.05070","repositories_listed":1,"syntology":null},{"url":null,"slug":"pessimism-principle-can-be-effective-towards","title":"Pessimism Principle Can Be Effective: Towards a Framework for Zero-Shot Transfer Reinforcement Learning","date":"2025-05-24","arxiv_id":"2505.18447","repositories_listed":0,"syntology":null},{"url":null,"slug":"beam-selection-in-isac-using-contextual","title":"Beam Selection in ISAC using Contextual Bandit with Multi-modal Transformer and Transfer Learning","date":"2025-03-11","arxiv_id":"2503.08937","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-limits-of-transfer-reinforcement-learning","title":"The Limits of Transfer Reinforcement Learning with Latent Low-rank Structure","date":"2024-10-28","arxiv_id":"2410.21601","repositories_listed":0,"syntology":null},{"url":null,"slug":"transfer-reinforcement-learning-in","title":"Transfer Reinforcement Learning in Heterogeneous Action Spaces using Subgoal Mapping","date":"2024-10-18","arxiv_id":"2410.14484","repositories_listed":0,"syntology":null},{"url":null,"slug":"sf-dqn-provable-knowledge-transfer-using","title":"SF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning","date":"2024-05-24","arxiv_id":"2405.15920","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-overview-of-machine-learning-enabled-1","title":"An Overview of Machine Learning-Enabled Optimization for Reconfigurable Intelligent Surfaces-Aided 6G Networks: From Reinforcement Learning to Large Language Models","date":"2024-05-09","arxiv_id":"2405.17439","repositories_listed":0,"syntology":null},{"url":null,"slug":"enabling-multi-agent-transfer-reinforcement","title":"Enabling Multi-Agent Transfer Reinforcement Learning via Scenario Independent Representation","date":"2024-02-13","arxiv_id":"2402.08184","repositories_listed":0,"syntology":null},{"url":null,"slug":"value-explicit-pretraining-for-goal-based","title":"Value Explicit Pretraining for Learning Transferable Representations","date":"2023-12-19","arxiv_id":"2312.12339","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-multi-task-and-transfer","title":"Efficient Multi-Task and Transfer Reinforcement Learning with Parameter-Compositional Framework","date":"2023-06-02","arxiv_id":"2306.01839","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-in-the-wild-with","title":"Reinforcement Learning in the Wild with Maximum Likelihood-based Model Transfer","date":"2023-02-18","arxiv_id":"2302.09273","repositories_listed":0,"syntology":null},{"url":null,"slug":"provably-sample-efficient-rl-with-side","title":"Provably Sample-Efficient RL with Side Information about Latent Dynamics","date":"2022-05-27","arxiv_id":"2205.14237","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-from-peers-transfer-reinforcement","title":"Learning from Peers: Deep Transfer Reinforcement Learning for Joint Radio and Cache Resource Allocation in 5G RAN Slicing","date":"2021-09-16","arxiv_id":"2109.07999","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-without-knowing-unobserved-context","title":"Learning without Knowing: Unobserved Context in Continuous Transfer Reinforcement Learning","date":"2021-06-07","arxiv_id":"2106.03833","repositories_listed":0,"syntology":null},{"url":null,"slug":"procedural-content-generation-better","title":"Procedural Content Generation: Better Benchmarks for Transfer Reinforcement Learning","date":"2021-05-31","arxiv_id":"2105.14780","repositories_listed":0,"syntology":null},{"url":null,"slug":"learn-dynamic-aware-state-embedding-for","title":"Learn Dynamic-Aware State Embedding for Transfer Learning","date":"2021-01-06","arxiv_id":"2101.02230","repositories_listed":0,"syntology":null},{"url":null,"slug":"modular-transfer-learning-with-transition","title":"Modular Transfer Learning with Transition Mismatch Compensation for Excessive Disturbance Rejection","date":"2020-07-29","arxiv_id":"2007.14646","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-energy-management-for-real-driving","title":"Adaptive Energy Management for Real Driving Conditions via Transfer Reinforcement Learning","date":"2020-07-24","arxiv_id":"2007.12560","repositories_listed":0,"syntology":null},{"url":null,"slug":"transfer-reinforcement-learning-under","title":"Transfer Reinforcement Learning under Unobserved Contextual Information","date":"2020-03-09","arxiv_id":"2003.04427","repositories_listed":0,"syntology":null},{"url":null,"slug":"universal-successor-features-for-transfer-1","title":"Universal Successor Features for Transfer Reinforcement Learning","date":"2020-01-05","arxiv_id":"2001.04025","repositories_listed":0,"syntology":null},{"url":null,"slug":"does-knowledge-transfer-always-help-to-learn","title":"How Does an Approximate Model Help in Reinforcement Learning?","date":"2019-12-06","arxiv_id":"1912.02986","repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-transfer-reinforcement-learning-for","title":"Federated Transfer Reinforcement Learning for Autonomous Driving","date":"2019-10-14","arxiv_id":"1910.06001","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalization-in-transfer-learning","title":"Generalization in Transfer Learning","date":"2019-09-03","arxiv_id":"1909.01331","repositories_listed":0,"syntology":null},{"url":null,"slug":"bayesian-transfer-reinforcement-learning-with","title":"Bayesian Transfer Reinforcement Learning with Prior Knowledge Rules","date":"2018-09-30","arxiv_id":"1810.00468","repositories_listed":0,"syntology":null},{"url":null,"slug":"vpe-variational-policy-embedding-for-transfer","title":"VPE: Variational Policy Embedding for Transfer Reinforcement Learning","date":"2018-09-10","arxiv_id":"1809.03548","repositories_listed":0,"syntology":null},{"url":null,"slug":"universal-successor-representations-for","title":"Universal Successor Representations for Transfer Reinforcement Learning","date":"2018-04-11","arxiv_id":"1804.03758","repositories_listed":0,"syntology":null},{"url":null,"slug":"personalizing-a-dialogue-system-with-transfer","title":"Personalizing a Dialogue System with Transfer Reinforcement Learning","date":"2016-10-10","arxiv_id":"1610.02891","repositories_listed":0,"syntology":null},{"url":null,"slug":"transfer-from-multiple-mdps","title":"Transfer from Multiple MDPs","date":"2011-12-01","arxiv_id":null,"repositories_listed":0,"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"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/task/transfer-reinforcement-learning/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/transfer-reinforcement-learning/papers/ran/1","json":"/task/transfer-reinforcement-learning/papers/ran/1.json","rows":2}],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"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"},"record_sha256":"54b21971e4c951dc00301a0492fb0ccc48f69552a0d45315880c72d719630afc","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}