{"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/deep-reinforcement-learning/papers/59","list_of":"/task/deep-reinforcement-learning","task":"Deep Reinforcement Learning","archive":{"snapshot":"2025-07-28"},"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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":59,"pages_in_order":59,"rows_per_page":100,"rows":[5801,5822],"of":5822,"counts":{"archive_papers_tagged":5822,"with_a_code_link":1739,"where_syntology_ran_a_sample":398,"not_listed_spam_title":0,"listed":5822,"listed_where_code_ran":398,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":340,"every_run_a_failure_of_syntologys_instrument":58,"listed_with_a_run_with_no_instrument_failure":340,"listed_every_run_a_failure_of_syntologys_instrument":58,"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"},"first_page":"/task/deep-reinforcement-learning","prev":"/task/deep-reinforcement-learning/papers/58","next":null,"papers":[{"url":null,"slug":"learning-modular-neural-network-policies-for","title":"Learning Modular Neural Network Policies for Multi-Task and Multi-Robot Transfer","date":"2016-09-22","arxiv_id":"1609.07088","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-deep-symbolic-reinforcement-learning","title":"Towards Deep Symbolic Reinforcement Learning","date":"2016-09-18","arxiv_id":"1609.05518","repositories_listed":0,"syntology":null},{"url":null,"slug":"interactive-spoken-content-retrieval-by-deep","title":"Interactive Spoken Content Retrieval by Deep Reinforcement Learning","date":"2016-09-16","arxiv_id":"1609.05234","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-simulation-for-robot-arm-control-with-deep","title":"3D Simulation for Robot Arm Control with Deep Q-Learning","date":"2016-09-13","arxiv_id":"1609.03759","repositories_listed":0,"syntology":null},{"url":null,"slug":"bbq-networks-efficient-exploration-in-deep-1","title":"BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems","date":"2016-08-17","arxiv_id":"1608.05081","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-bridge-bidding-using-deep","title":"Automatic Bridge Bidding Using Deep Reinforcement Learning","date":"2016-07-12","arxiv_id":"1607.03290","repositories_listed":0,"syntology":null},{"url":null,"slug":"visualizing-dynamics-from-t-sne-to-semi-mdps","title":"Visualizing Dynamics: from t-SNE to SEMI-MDPs","date":"2016-06-22","arxiv_id":"1606.07112","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-discovers","title":"Deep Reinforcement Learning Discovers Internal Models","date":"2016-06-16","arxiv_id":"1606.05174","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-with-macro","title":"Deep Reinforcement Learning With Macro-Actions","date":"2016-06-15","arxiv_id":"1606.04615","repositories_listed":0,"syntology":null},{"url":null,"slug":"policy-networks-with-two-stage-training-for","title":"Policy Networks with Two-Stage Training for Dialogue Systems","date":"2016-06-10","arxiv_id":"1606.03152","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-q-networks-for-accelerating-the-training","title":"Deep Q-Networks for Accelerating the Training of Deep Neural Networks","date":"2016-06-05","arxiv_id":"1606.01467","repositories_listed":0,"syntology":null},{"url":null,"slug":"control-of-memory-active-perception-and","title":"Control of Memory, Active Perception, and Action in Minecraft","date":"2016-05-30","arxiv_id":"1605.09128","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-frame-skip-deep-q-network","title":"Dynamic Frame skip Deep Q Network","date":"2016-05-17","arxiv_id":"1605.05365","repositories_listed":0,"syntology":null},{"url":null,"slug":"classifying-options-for-deep-reinforcement","title":"Classifying Options for Deep Reinforcement Learning","date":"2016-04-27","arxiv_id":"1604.08153","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-hierarchical-approach-to-lifelong","title":"A Deep Hierarchical Approach to Lifelong Learning in Minecraft","date":"2016-04-25","arxiv_id":"1604.07255","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-communicate-to-solve-riddles-with","title":"Learning to Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networks","date":"2016-02-08","arxiv_id":"1602.02672","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-to-discount-deep-reinforcement-learning","title":"How to Discount Deep Reinforcement Learning: Towards New Dynamic Strategies","date":"2015-12-07","arxiv_id":"1512.02011","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-with-attention","title":"Deep Reinforcement Learning with Attention for Slate Markov Decision Processes with High-Dimensional States and Actions","date":"2015-12-03","arxiv_id":"1512.01124","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-vision-based-deep-reinforcement","title":"Towards Vision-Based Deep Reinforcement Learning for Robotic Motion Control","date":"2015-11-12","arxiv_id":"1511.03791","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-text-with-deep-reinforcement","title":"Generating Text with Deep Reinforcement Learning","date":"2015-10-30","arxiv_id":"1510.09202","repositories_listed":0,"syntology":null},{"url":null,"slug":"compatible-value-gradients-for-reinforcement","title":"Compatible Value Gradients for Reinforcement Learning of Continuous Deep Policies","date":"2015-09-10","arxiv_id":"1509.03005","repositories_listed":0,"syntology":null},{"url":null,"slug":"autonomous-crm-control-via-clv-approximation","title":"Autonomous CRM Control via CLV Approximation with Deep Reinforcement Learning in Discrete and Continuous Action Space","date":"2015-04-08","arxiv_id":"1504.01840","repositories_listed":0,"syntology":null}],"record_sha256":"e165a79022d24aab27e43d860212d97d7d8e27d9ef087bb9a2180c5d242b9946","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}