{"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/56","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":56,"pages_in_order":59,"rows_per_page":100,"rows":[5501,5600],"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/55","next":"/task/deep-reinforcement-learning/papers/57","papers":[{"url":null,"slug":"improving-on-policy-learning-with-statistical","title":"Improving On-policy Learning with Statistical Reward Accumulation","date":"2018-09-07","arxiv_id":"1809.02387","repositories_listed":0,"syntology":null},{"url":null,"slug":"ans-adaptive-network-scaling-for-deep","title":"ANS: Adaptive Network Scaling for Deep Rectifier Reinforcement Learning Models","date":"2018-09-06","arxiv_id":"1809.02112","repositories_listed":0,"syntology":null},{"url":null,"slug":"learn-what-not-to-learn-action-elimination","title":"Learn What Not to Learn: Action Elimination with Deep Reinforcement Learning","date":"2018-09-06","arxiv_id":"1809.02121","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-based-regularization-for-deep","title":"Model-Based Regularization for Deep Reinforcement Learning with Transcoder Networks","date":"2018-09-06","arxiv_id":"1809.01906","repositories_listed":0,"syntology":null},{"url":null,"slug":"transferring-deep-reinforcement-learning-with","title":"Transferring Deep Reinforcement Learning with Adversarial Objective and Augmentation","date":"2018-09-04","arxiv_id":"1809.00770","repositories_listed":0,"syntology":null},{"url":null,"slug":"effective-exploration-for-deep-reinforcement","title":"Effective Exploration for Deep Reinforcement Learning via Bootstrapped Q-Ensembles under Tsallis Entropy Regularization","date":"2018-09-02","arxiv_id":"1809.00403","repositories_listed":0,"syntology":null},{"url":null,"slug":"natural-language-person-search-using-deep","title":"Natural Language Person Search Using Deep Reinforcement Learning","date":"2018-09-02","arxiv_id":"1809.00365","repositories_listed":0,"syntology":null},{"url":null,"slug":"collaborative-deep-reinforcement-learning-for","title":"Collaborative Deep Reinforcement Learning for Multi-Object Tracking","date":"2018-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-with-iterative","title":"Deep Reinforcement Learning with Iterative Shift for Visual Tracking","date":"2018-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dual-agent-deep-reinforcement-learning-for","title":"Dual-Agent Deep Reinforcement Learning for Deformable Face Tracking","date":"2018-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"goal-oriented-visual-question-generation-via","title":"Goal-Oriented Visual Question Generation via Intermediate Rewards","date":"2018-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"part-activated-deep-reinforcement-learning","title":"Part-Activated Deep Reinforcement Learning for Action Prediction","date":"2018-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/navigationnet-a-large-scale-interactive","slug":"navigationnet-a-large-scale-interactive","title":"NavigationNet: A Large-scale Interactive Indoor Navigation Dataset","date":"2018-08-25","arxiv_id":"1808.08374","repositories_listed":0,"syntology":null},{"url":null,"slug":"importance-mixing-improving-sample-reuse-in","title":"Importance mixing: Improving sample reuse in evolutionary policy search methods","date":"2018-08-17","arxiv_id":"1808.05832","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-sensor-network-reconfiguration-with","title":"Visual Sensor Network Reconfiguration with Deep Reinforcement Learning","date":"2018-08-13","arxiv_id":"1808.04287","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-active-object-tracking-and-its","title":"End-to-end Active Object Tracking and Its Real-world Deployment via Reinforcement Learning","date":"2018-08-10","arxiv_id":"1808.03405","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-new-concept-of-deep-reinforcement-learning-1","title":"A New Concept of Deep Reinforcement Learning based Augmented General Tagging System","date":"2018-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"interpretable-rationale-augmented-charge","title":"Interpretable Rationale Augmented Charge Prediction System","date":"2018-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"structured-dialogue-policy-with-graph-neural","title":"Structured Dialogue Policy with Graph Neural Networks","date":"2018-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"active-object-perceiver-recognition-guided","title":"Active Object Perceiver: Recognition-guided Policy Learning for Object Searching on Mobile Robots","date":"2018-07-30","arxiv_id":"1807.11174","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-spatiotemporal-self-supervision-by","title":"Improving Spatiotemporal Self-Supervision by Deep Reinforcement Learning","date":"2018-07-30","arxiv_id":"1807.11293","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-interrupt-a-hierarchical-deep","title":"Learning to Interrupt: A Hierarchical Deep Reinforcement Learning Framework for Efficient Exploration","date":"2018-07-30","arxiv_id":"1807.11150","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-play-pong-using-policy-gradient","title":"Learning to Play Pong using Policy Gradient Learning","date":"2018-07-23","arxiv_id":"1807.08452","repositories_listed":0,"syntology":null},{"url":null,"slug":"asynchronous-advantage-actor-critic-agent-for","title":"Asynchronous Advantage Actor-Critic Agent for Starcraft II","date":"2018-07-22","arxiv_id":"1807.08217","repositories_listed":0,"syntology":null},{"url":null,"slug":"navren-rl-learning-to-fly-in-real-environment","title":"NAVREN-RL: Learning to fly in real environment via end-to-end deep reinforcement learning using monocular images","date":"2018-07-22","arxiv_id":"1807.08241","repositories_listed":0,"syntology":null},{"url":null,"slug":"fuzzergym-a-competitive-framework-for-fuzzing","title":"FuzzerGym: A Competitive Framework for Fuzzing and Learning","date":"2018-07-19","arxiv_id":"1807.07490","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-robust-policy-learning-in-the-presence","title":"Online Robust Policy Learning in the Presence of Unknown Adversaries","date":"2018-07-16","arxiv_id":"1807.06064","repositories_listed":0,"syntology":null},{"url":null,"slug":"toward-interpretable-deep-reinforcement","title":"Toward Interpretable Deep Reinforcement Learning with Linear Model U-Trees","date":"2018-07-16","arxiv_id":"1807.05887","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-bottleneck-simulator-a-model-based-deep","title":"The Bottleneck Simulator: A Model-based Deep Reinforcement Learning Approach","date":"2018-07-12","arxiv_id":"1807.04723","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-summarisation-by-classification-with","title":"Video Summarisation by Classification with Deep Reinforcement Learning","date":"2018-07-09","arxiv_id":"1807.03089","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-race-driving-with-deep","title":"End-to-End Race Driving with Deep Reinforcement Learning","date":"2018-07-06","arxiv_id":"1807.02371","repositories_listed":0,"syntology":null},{"url":null,"slug":"arcades-a-deep-model-for-adaptive-decision","title":"Arcades: A deep model for adaptive decision making in voice controlled smart-home","date":"2018-07-05","arxiv_id":"1807.01970","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-doom-using","title":"Deep Reinforcement Learning for Doom using Unsupervised Auxiliary Tasks","date":"2018-07-05","arxiv_id":"1807.01960","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-level-performance-in-first-person","title":"Human-level performance in first-person multiplayer games with population-based deep reinforcement learning","date":"2018-07-03","arxiv_id":"1807.01281","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-nlp","title":"Deep Reinforcement Learning for NLP","date":"2018-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-mixed-optimization-for-reinforcement","title":"Towards Mixed Optimization for Reinforcement Learning with Program Synthesis","date":"2018-07-01","arxiv_id":"1807.00403","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-exploration-strategy-for-self","title":"Adversarial Active Exploration for Inverse Dynamics Model Learning","date":"2018-06-26","arxiv_id":"1806.10019","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-an-overview-1","title":"Deep Reinforcement Learning: An Overview","date":"2018-06-23","arxiv_id":"1806.08894","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-ask-knowledge-acquisition-via-20","title":"Learning-to-Ask: Knowledge Acquisition via 20 Questions","date":"2018-06-22","arxiv_id":"1806.08554","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-new-approach-for-resource-scheduling-with","title":"A New Approach for Resource Scheduling with Deep Reinforcement Learning","date":"2018-06-21","arxiv_id":"1806.08122","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-dissection-of-overfitting-and","title":"A Dissection of Overfitting and Generalization in Continuous Reinforcement Learning","date":"2018-06-20","arxiv_id":"1806.07937","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-policy-representations-in-multiagent","title":"Learning Policy Representations in Multiagent Systems","date":"2018-06-17","arxiv_id":"1806.06464","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-width-based-planning-with-compact","title":"Improving width-based planning with compact policies","date":"2018-06-15","arxiv_id":"1806.05898","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-dynamic-urban","title":"Deep Reinforcement Learning for Dynamic Urban Transportation Problems","date":"2018-06-14","arxiv_id":"1806.05310","repositories_listed":0,"syntology":null},{"url":null,"slug":"meta-learning-transferable-active-learning","title":"Meta-Learning Transferable Active Learning Policies by Deep Reinforcement Learning","date":"2018-06-12","arxiv_id":"1806.04798","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-deep-reinforcement-learning-with-1","title":"Multi-Agent Deep Reinforcement Learning with Human Strategies","date":"2018-06-12","arxiv_id":"1806.04562","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-view-planning-with-multi-scale-deep","title":"Automatic View Planning with Multi-scale Deep Reinforcement Learning Agents","date":"2018-06-08","arxiv_id":"1806.03228","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-reinforcement-learning-framework","title":"Adversarial Reinforcement Learning Framework for Benchmarking Collision Avoidance Mechanisms in Autonomous Vehicles","date":"2018-06-04","arxiv_id":"1806.01368","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigation-of-policy-manipulation-attacks-on","title":"Mitigation of Policy Manipulation Attacks on Deep Q-Networks with Parameter-Space Noise","date":"2018-06-04","arxiv_id":"1806.02190","repositories_listed":0,"syntology":null},{"url":null,"slug":"relational-inductive-bias-for-physical","title":"Relational inductive bias for physical construction in humans and machines","date":"2018-06-04","arxiv_id":"1806.01203","repositories_listed":0,"syntology":null},{"url":null,"slug":"building-advanced-dialogue-managers-for-goal","title":"Building Advanced Dialogue Managers for Goal-Oriented Dialogue Systems","date":"2018-06-03","arxiv_id":"1806.00780","repositories_listed":0,"syntology":null},{"url":null,"slug":"daqn-deep-auto-encoder-and-q-network","title":"DAQN: Deep Auto-encoder and Q-Network","date":"2018-06-02","arxiv_id":"1806.00630","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-entropy-for-policy-gradient-with","title":"Efficient Entropy for Policy Gradient with Multidimensional Action Space","date":"2018-06-02","arxiv_id":"1806.00589","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-curiosity-search-intra-life-exploration","title":"Deep Curiosity Search: Intra-Life Exploration Can Improve Performance on Challenging Deep Reinforcement Learning Problems","date":"2018-06-01","arxiv_id":"1806.00553","repositories_listed":0,"syntology":null},{"url":"/paper/deep-progressive-reinforcement-learning-for","slug":"deep-progressive-reinforcement-learning-for","title":"Deep Progressive Reinforcement Learning for Skeleton-Based Action Recognition","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"graphbit-bitwise-interaction-mining-via-deep","title":"GraphBit: Bitwise Interaction Mining via Deep Reinforcement Learning","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"integrating-episodic-memory-into-a","title":"Integrating Episodic Memory into a Reinforcement Learning Agent using Reservoir Sampling","date":"2018-06-01","arxiv_id":"1806.00540","repositories_listed":0,"syntology":null},{"url":null,"slug":"mining-evidences-for-concept-stock","title":"Mining Evidences for Concept Stock Recommendation","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-cutting-agent-learning-for","title":"Reinforcement Cutting-Agent Learning for Video Object Segmentation","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-construction-and-reasoning-of","title":"Scalable Construction and Reasoning of Massive Knowledge Bases","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"seednet-automatic-seed-generation-with-deep","title":"SeedNet: Automatic Seed Generation With Deep Reinforcement Learning for Robust Interactive Segmentation","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sint-robust-visual-tracking-via-adversarial","title":"SINT++: Robust Visual Tracking via Adversarial Positive Instance Generation","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"observe-and-look-further-achieving-consistent","title":"Observe and Look Further: Achieving Consistent Performance on Atari","date":"2018-05-29","arxiv_id":"1805.11593","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-in-ice-hockey-for","title":"Deep Reinforcement Learning in Ice Hockey for Context-Aware Player Evaluation","date":"2018-05-26","arxiv_id":"1805.11088","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-self-imitating-diverse-policies","title":"Learning Self-Imitating Diverse Policies","date":"2018-05-25","arxiv_id":"1805.10309","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-centralized-deep-multi-agent","title":"Scalable Centralized Deep Multi-Agent Reinforcement Learning via Policy Gradients","date":"2018-05-22","arxiv_id":"1805.08776","repositories_listed":0,"syntology":null},{"url":"/paper/hierarchically-structured-reinforcement","slug":"hierarchically-structured-reinforcement","title":"Hierarchically Structured Reinforcement Learning for Topically Coherent Visual Story Generation","date":"2018-05-21","arxiv_id":"1805.08191","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-resource","title":"Deep Reinforcement Learning for Resource Management in Network Slicing","date":"2018-05-17","arxiv_id":"1805.06591","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-expansion-in-text-based-games","title":"Language Expansion In Text-Based Games","date":"2018-05-17","arxiv_id":"1805.07274","repositories_listed":0,"syntology":null},{"url":null,"slug":"follownet-robot-navigation-by-following","title":"FollowNet: Robot Navigation by Following Natural Language Directions with Deep Reinforcement Learning","date":"2018-05-16","arxiv_id":"1805.06150","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimized-computation-offloading-performance","title":"Optimized Computation Offloading Performance in Virtual Edge Computing Systems via Deep Reinforcement Learning","date":"2018-05-16","arxiv_id":"1805.06146","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-hierarchical-reinforcement-learning","title":"Deep Hierarchical Reinforcement Learning Algorithm in Partially Observable Markov Decision Processes","date":"2018-05-11","arxiv_id":"1805.04419","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-optimal","title":"Deep Reinforcement Learning for Optimal Control of Space Heating","date":"2018-05-10","arxiv_id":"1805.03777","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-page-wise","title":"Deep Reinforcement Learning for Page-wise Recommendations","date":"2018-05-07","arxiv_id":"1805.02343","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploration-by-distributional-reinforcement","title":"Exploration by Distributional Reinforcement Learning","date":"2018-05-04","arxiv_id":"1805.01907","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-deep-reinforcement-learning-for","title":"Robust Deep Reinforcement Learning for Security and Safety in Autonomous Vehicle Systems","date":"2018-05-02","arxiv_id":"1805.00983","repositories_listed":0,"syntology":null},{"url":null,"slug":"falsification-of-cyber-physical-systems-using","title":"Falsification of Cyber-Physical Systems Using Deep Reinforcement Learning","date":"2018-05-01","arxiv_id":"1805.00200","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-to-acquire","title":"Deep Reinforcement Learning to Acquire Navigation Skills for Wheel-Legged Robots in Complex Environments","date":"2018-04-27","arxiv_id":"1804.10500","repositories_listed":0,"syntology":null},{"url":null,"slug":"sim-to-real-learning-agile-locomotion-for","title":"Sim-to-Real: Learning Agile Locomotion For Quadruped Robots","date":"2018-04-27","arxiv_id":"1804.10332","repositories_listed":0,"syntology":null},{"url":null,"slug":"cell-selection-with-deep-reinforcement","title":"Cell Selection with Deep Reinforcement Learning in Sparse Mobile Crowdsensing","date":"2018-04-19","arxiv_id":"1804.07047","repositories_listed":0,"syntology":null},{"url":"/paper/learning-to-extract-coherent-summary-via-deep","slug":"learning-to-extract-coherent-summary-via-deep","title":"Learning to Extract Coherent Summary via Deep Reinforcement Learning","date":"2018-04-19","arxiv_id":"1804.07036","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-vehicles-behavior-decision-making","title":"Automated vehicle's behavior decision making using deep reinforcement learning and high-fidelity simulation environment","date":"2018-04-17","arxiv_id":"1804.06264","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-improving-deep-reinforcement-learning-for-1","title":"On Improving Deep Reinforcement Learning for POMDPs","date":"2018-04-17","arxiv_id":"1804.06309","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-how-to-self-learn-enhancing-self","title":"Learning How to Self-Learn: Enhancing Self-Training Using Neural Reinforcement Learning","date":"2018-04-16","arxiv_id":"1804.05734","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-modality-sensor-data-classification","title":"Multi-modality Sensor Data Classification with Selective Attention","date":"2018-04-16","arxiv_id":"1804.05493","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-dual-view-deep-agent","title":"Robust Dual View Deep Agent","date":"2018-04-13","arxiv_id":"1804.05120","repositories_listed":0,"syntology":null},{"url":null,"slug":"distort-and-recover-color-enhancement-using","title":"Distort-and-Recover: Color Enhancement using Deep Reinforcement Learning","date":"2018-04-12","arxiv_id":"1804.04450","repositories_listed":0,"syntology":null},{"url":null,"slug":"feature-based-aggregation-and-deep","title":"Feature-Based Aggregation and Deep Reinforcement Learning: A Survey and Some New Implementations","date":"2018-04-12","arxiv_id":"1804.04577","repositories_listed":0,"syntology":null},{"url":null,"slug":"outline-objects-using-deep-reinforcement","title":"Outline Objects using Deep Reinforcement Learning","date":"2018-04-10","arxiv_id":"1804.04603","repositories_listed":0,"syntology":null},{"url":null,"slug":"programmatically-interpretable-reinforcement","title":"Programmatically Interpretable Reinforcement Learning","date":"2018-04-06","arxiv_id":"1804.02477","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-human-mixed-strategy-approach-to-deep","title":"A Human Mixed Strategy Approach to Deep Reinforcement Learning","date":"2018-04-05","arxiv_id":"1804.01874","repositories_listed":0,"syntology":null},{"url":null,"slug":"information-maximizing-exploration-with-a","title":"Information Maximizing Exploration with a Latent Dynamics Model","date":"2018-04-04","arxiv_id":"1804.01238","repositories_listed":0,"syntology":null},{"url":null,"slug":"emorl-continuous-acoustic-emotion","title":"EmoRL: Continuous Acoustic Emotion Classification using Deep Reinforcement Learning","date":"2018-04-03","arxiv_id":"1804.04053","repositories_listed":0,"syntology":null},{"url":null,"slug":"curiosity-driven-exploration-for-mapless","title":"Curiosity-driven Exploration for Mapless Navigation with Deep Reinforcement Learning","date":"2018-04-02","arxiv_id":"1804.00456","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-run-challenge-synthesizing","title":"Learning to Run challenge: Synthesizing physiologically accurate motion using deep reinforcement learning","date":"2018-03-31","arxiv_id":"1804.00198","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-with-model","title":"Deep Reinforcement Learning with Model Learning and Monte Carlo Tree Search in Minecraft","date":"2018-03-22","arxiv_id":"1803.08456","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-state-representations-for-query","title":"Learning State Representations for Query Optimization with Deep Reinforcement Learning","date":"2018-03-22","arxiv_id":"1803.08604","repositories_listed":0,"syntology":null},{"url":null,"slug":"natural-gradient-deep-q-learning","title":"Natural Gradient Deep Q-learning","date":"2018-03-20","arxiv_id":"1803.07482","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-sponsored-search-ranking-strategy","title":"Optimizing Sponsored Search Ranking Strategy by Deep Reinforcement Learning","date":"2018-03-20","arxiv_id":"1803.07347","repositories_listed":0,"syntology":null},{"url":null,"slug":"variance-reduction-for-policy-gradient-with","title":"Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines","date":"2018-03-20","arxiv_id":"1803.07246","repositories_listed":0,"syntology":null}],"record_sha256":"2f4cd6fac69f8e36e2a937fbb6d39afc5573b5ce04d1fb003d8d8f8eb137e4ea","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}