{"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/reinforcement-learning-2/papers/113","list_of":"/task/reinforcement-learning-2","task":"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":113,"pages_in_order":135,"rows_per_page":100,"rows":[11201,11300],"of":13427,"counts":{"archive_papers_tagged":13427,"with_a_code_link":4119,"where_syntology_ran_a_sample":1165,"not_listed_spam_title":0,"listed":13427,"listed_where_code_ran":1165,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":973,"every_run_a_failure_of_syntologys_instrument":192,"listed_with_a_run_with_no_instrument_failure":973,"listed_every_run_a_failure_of_syntologys_instrument":192,"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/reinforcement-learning-2","prev":"/task/reinforcement-learning-2/papers/112","next":"/task/reinforcement-learning-2/papers/114","papers":[{"url":null,"slug":"learning-reusable-options-for-multi-task-1","title":"Learning Reusable Options for Multi-Task Reinforcement Learning","date":"2020-01-06","arxiv_id":"2001.01577","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimal-options-for-multi-task-reinforcement","title":"Optimal Options for Multi-Task Reinforcement Learning Under Time Constraints","date":"2020-01-06","arxiv_id":"2001.01620","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":"hierarchical-reinforcement-learning-as-a","title":"Hierarchical Reinforcement Learning as a Model of Human Task Interleaving","date":"2020-01-04","arxiv_id":"2001.02122","repositories_listed":0,"syntology":null},{"url":null,"slug":"intelligent-roundabout-insertion-using-deep","title":"Intelligent Roundabout Insertion using Deep Reinforcement Learning","date":"2020-01-03","arxiv_id":"2001.00786","repositories_listed":0,"syntology":null},{"url":"/paper/making-sense-of-reinforcement-learning-and-1","slug":"making-sense-of-reinforcement-learning-and-1","title":"Making Sense of Reinforcement Learning and Probabilistic Inference","date":"2020-01-03","arxiv_id":"2001.00805","repositories_listed":0,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/making-sense-of-reinforcement-learning-and-1#ran","syntology_url":"https://syntology.ai/paper/2001.00805","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.00805"}},"official":null}},{"url":null,"slug":"continuous-discrete-reinforcement-learning","title":"Continuous-Discrete Reinforcement Learning for Hybrid Control in Robotics","date":"2020-01-02","arxiv_id":"2001.00449","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-goal-and-strategy-inference-across","title":"Joint Goal and Strategy Inference across Heterogeneous Demonstrators via Reward Network Distillation","date":"2020-01-02","arxiv_id":"2001.00503","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-reinforcement-learning-with-deep","title":"Zero-Shot Reinforcement Learning with Deep Attention Convolutional Neural Networks","date":"2020-01-02","arxiv_id":"2001.00605","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-game-theoretic-perspective-on-model-based","title":"A Game Theoretic Perspective on Model-Based Reinforcement Learning","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-droplet-routing-in-digital","title":"Adaptive Droplet Routing in Digital Microfluidic Biochips Using Deep Reinforcement Learning","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"batch-reinforcement-learning-with","title":"Batch Reinforcement Learning with Hyperparameter Gradients","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"breaking-the-curse-of-many-agents-provable-1","title":"Breaking the Curse of Many Agents: Provable Mean Embedding $Q$-Iteration for Mean-Field Reinforcement Learning","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-randomized-least-squares-value-iteration","title":"Deep Randomized Least Squares Value Iteration","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-with-implicit","title":"Deep Reinforcement Learning with Implicit Human Feedback","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-with-smooth-1","title":"Deep Reinforcement Learning with Smooth Policy","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"designing-optimal-dynamic-treatment-regimes-a","title":"Designing Optimal Dynamic Treatment Regimes: A Causal Reinforcement Learning Approach","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"double-reinforcement-learning-for-efficient-1","title":"Double Reinforcement Learning for Efficient and Robust Off-Policy Evaluation","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-adversarial-imitation-learning-3","title":"Generative Adversarial Imitation Learning with Neural Network Parameterization: Global Optimality and Convergence Rate","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"inductive-bias-driven-reinforcement-learning-1","title":"Inductive Bias-driven Reinforcement Learning For Efficient Schedules in Heterogeneous Clusters","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-general-purpose-controllers-via","title":"Learning General-Purpose Controllers via Locally Communicating Sensorimotor Modules","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-representations-in-reinforcement-1","title":"Learning Representations in Reinforcement Learning: an Information Bottleneck Approach","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-multiagent-cooperation-via-policy","title":"Optimizing Multiagent Cooperation via Policy Evolution and Shared Experiences","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"options-as-responses-grounding-behavioural-1","title":"OPtions as REsponses: Grounding behavioural hierarchies in multi-agent reinforcement learning","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-with-differential","title":"Reinforcement Learning with Differential Privacy","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-with-goal-distance","title":"Reinforcement Learning with Goal-Distance Gradient","date":"2020-01-01","arxiv_id":"2001.00127","repositories_listed":0,"syntology":null},{"url":null,"slug":"responsive-safety-in-reinforcement-learning-1","title":"Responsive Safety in Reinforcement Learning","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"svqn-sequential-variational-soft-q-learning","title":"SVQN: Sequential Variational Soft Q-Learning Networks","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-natural-lottery-ticket-winner","title":"The Natural Lottery Ticket Winner: Reinforcement Learning with Ordinary Neural Circuits","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"way-off-policy-batch-deep-reinforcement-1","title":"Way Off-Policy Batch Deep Reinforcement Learning of Human Preferences in Dialog","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"information-theoretic-model-predictive-q-1","title":"Information Theoretic Model Predictive Q-Learning","date":"2019-12-31","arxiv_id":"2001.02153","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-gamblers-problem-and-beyond-1","title":"The Gambler's Problem and Beyond","date":"2019-12-31","arxiv_id":"2001.00102","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-based-out-of-distribution-1","title":"Uncertainty-Based Out-of-Distribution Classification in Deep Reinforcement Learning","date":"2019-12-31","arxiv_id":"2001.00496","repositories_listed":0,"syntology":null},{"url":null,"slug":"world-programs-for-model-based-learning-and","title":"World Programs for Model-Based Learning and Planning in Compositional State and Action Spaces","date":"2019-12-30","arxiv_id":"1912.13007","repositories_listed":0,"syntology":null},{"url":null,"slug":"augmented-replay-memory-in-reinforcement","title":"Augmented Replay Memory in Reinforcement Learning With Continuous Control","date":"2019-12-29","arxiv_id":"1912.12719","repositories_listed":0,"syntology":null},{"url":null,"slug":"computational-model-discovery-with","title":"Computational model discovery with reinforcement learning","date":"2019-12-29","arxiv_id":"2001.00008","repositories_listed":0,"syntology":null},{"url":null,"slug":"individual-specialization-in-multi-task","title":"Individual specialization in multi-task environments with multiagent reinforcement learners","date":"2019-12-29","arxiv_id":"1912.12671","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-policy-distillation-in-deep","title":"Real-time Policy Distillation in Deep Reinforcement Learning","date":"2019-12-29","arxiv_id":"1912.12630","repositories_listed":0,"syntology":null},{"url":null,"slug":"speeding-up-reinforcement-learning-by","title":"Speeding up reinforcement learning by combining attention and agency features","date":"2019-12-29","arxiv_id":"1912.12623","repositories_listed":0,"syntology":null},{"url":null,"slug":"crowdfunding-dynamics-tracking-a","title":"Crowdfunding Dynamics Tracking: A Reinforcement Learning Approach","date":"2019-12-27","arxiv_id":"1912.12016","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-complex","title":"Deep reinforcement learning for complex evaluation of one-loop diagrams in quantum field theory","date":"2019-12-27","arxiv_id":"1912.12322","repositories_listed":0,"syntology":null},{"url":null,"slug":"evolution-strategies-converges-to-finite","title":"Evolution Strategies Converges to Finite Differences","date":"2019-12-27","arxiv_id":"2001.01684","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantum-logic-gate-synthesis-as-a-markov","title":"Quantum Logic Gate Synthesis as a Markov Decision Process","date":"2019-12-27","arxiv_id":"1912.12002","repositories_listed":0,"syntology":null},{"url":null,"slug":"quasi-newton-trust-region-policy-optimization","title":"Quasi-Newton Trust Region Policy Optimization","date":"2019-12-26","arxiv_id":"1912.11912","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-combat-compounding-error-in-model-1","title":"Learning to Combat Compounding-Error in Model-Based Reinforcement Learning","date":"2019-12-24","arxiv_id":"1912.11206","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-deep-reinforcement-learning-in","title":"A Survey of Deep Reinforcement Learning in Video Games","date":"2019-12-23","arxiv_id":"1912.10944","repositories_listed":0,"syntology":null},{"url":null,"slug":"direct-and-indirect-reinforcement-learning","title":"Direct and indirect reinforcement learning","date":"2019-12-23","arxiv_id":"1912.10600","repositories_listed":0,"syntology":null},{"url":null,"slug":"hamilton-jacobi-bellman-equations-for-q","title":"Hamilton-Jacobi-Bellman Equations for Q-Learning in Continuous Time","date":"2019-12-23","arxiv_id":"1912.10697","repositories_listed":0,"syntology":null},{"url":null,"slug":"monte-carlo-tree-search-for-policy","title":"Monte-Carlo Tree Search for Policy Optimization","date":"2019-12-23","arxiv_id":"1912.10648","repositories_listed":0,"syntology":null},{"url":null,"slug":"energy-aware-multi-server-mobile-edge","title":"Energy-Aware Multi-Server Mobile Edge Computing: A Deep Reinforcement Learning Approach","date":"2019-12-22","arxiv_id":"1912.10485","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-reinforcement-learning-of-optimal","title":"Online Reinforcement Learning of Optimal Threshold Policies for Markov Decision Processes","date":"2019-12-21","arxiv_id":"1912.10325","repositories_listed":0,"syntology":null},{"url":null,"slug":"predictive-coding-for-boosting-deep-1","title":"Predictive Coding for Boosting Deep Reinforcement Learning with Sparse Rewards","date":"2019-12-21","arxiv_id":"1912.13414","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-the-potential-of-deep","title":"Exploiting the potential of deep reinforcement learning for classification tasks in high-dimensional and unstructured data","date":"2019-12-20","arxiv_id":"1912.09595","repositories_listed":0,"syntology":null},{"url":null,"slug":"mastering-complex-control-in-moba-games-with","title":"Mastering Complex Control in MOBA Games with Deep Reinforcement Learning","date":"2019-12-20","arxiv_id":"1912.09729","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-collision-avoidance-in-dense","title":"Optimizing Collision Avoidance in Dense Airspace using Deep Reinforcement Learning","date":"2019-12-20","arxiv_id":"1912.10146","repositories_listed":0,"syntology":null},{"url":null,"slug":"teaching-robots-to-perceive-time-a","title":"Teaching robots to perceive time -- A reinforcement learning approach (Extended version)","date":"2019-12-20","arxiv_id":"1912.10113","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-designed-rf-pulse","title":"Deep Reinforcement Learning Designed Shinnar-Le Roux RF Pulse using Root-Flipping: DeepRF_SLR","date":"2019-12-19","arxiv_id":"1912.09015","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-motion","title":"Deep Reinforcement Learning for Motion Planning of Mobile Robots","date":"2019-12-19","arxiv_id":"1912.09260","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-smart-home","title":"Deep Reinforcement Learning for Smart Home Energy Management","date":"2019-12-19","arxiv_id":"1909.10165","repositories_listed":0,"syntology":null},{"url":null,"slug":"extendable-nfv-integrated-control-method","title":"Extendable NFV-Integrated Control Method Using Reinforcement Learning","date":"2019-12-19","arxiv_id":"1912.09022","repositories_listed":0,"syntology":null},{"url":null,"slug":"analysing-deep-reinforcement-learning-agents","title":"Analysing Deep Reinforcement Learning Agents Trained with Domain Randomisation","date":"2019-12-18","arxiv_id":"1912.08324","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-the-neural-linear-model-for","title":"Benchmarking the Neural Linear Model for Regression","date":"2019-12-18","arxiv_id":"1912.08416","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-grow-control-of-materials-self","title":"Learning to grow: control of material self-assembly using evolutionary reinforcement learning","date":"2019-12-18","arxiv_id":"1912.08333","repositories_listed":0,"syntology":null},{"url":null,"slug":"taming-an-autonomous-surface-vehicle-for-path","title":"Taming an autonomous surface vehicle for path following and collision avoidance using deep reinforcement learning","date":"2019-12-18","arxiv_id":"1912.08578","repositories_listed":0,"syntology":null},{"url":null,"slug":"unpaired-image-enhancement-featuring","title":"Unpaired Image Enhancement Featuring Reinforcement-Learning-Controlled Image Editing Software","date":"2019-12-17","arxiv_id":"1912.07833","repositories_listed":0,"syntology":null},{"url":null,"slug":"coordination-in-adversarial-sequential-team","title":"Coordination in Adversarial Sequential Team Games via Multi-Agent Deep Reinforcement Learning","date":"2019-12-16","arxiv_id":"1912.07712","repositories_listed":0,"syntology":null},{"url":null,"slug":"karl-knowledge-aware-reasoning-memory","title":"KARL: Knowledge-Aware Reasoning Memory Modeling with Reinforcement Learning of Vector Space","date":"2019-12-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"planning-with-abstract-learned-models-while","title":"Planning with Abstract Learned Models While Learning Transferable Subtasks","date":"2019-12-16","arxiv_id":"1912.07544","repositories_listed":0,"syntology":null},{"url":null,"slug":"bayesian-linear-regression-on-deep","title":"Bayesian Linear Regression on Deep Representations","date":"2019-12-14","arxiv_id":"1912.06760","repositories_listed":0,"syntology":null},{"url":null,"slug":"fairness-in-multi-agent-reinforcement","title":"Fairness in Multi-agent Reinforcement Learning for Stock Trading","date":"2019-12-14","arxiv_id":"2001.00918","repositories_listed":0,"syntology":null},{"url":null,"slug":"natural-actor-critic-converges-globally-for","title":"Natural Actor-Critic Converges Globally for Hierarchical Linear Quadratic Regulator","date":"2019-12-14","arxiv_id":"1912.06875","repositories_listed":0,"syntology":null},{"url":null,"slug":"resolving-congestions-in-the-air-traffic","title":"Resolving Congestions in the Air Traffic Management Domain via Multiagent Reinforcement Learning Methods","date":"2019-12-14","arxiv_id":"1912.06860","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatial-influence-aware-reinforcement","title":"Spatial Influence-aware Reinforcement Learning for Intelligent Transportation System","date":"2019-12-14","arxiv_id":"1912.06880","repositories_listed":0,"syntology":null},{"url":null,"slug":"lessons-from-reinforcement-learning-for","title":"Lessons from reinforcement learning for biological representations of space","date":"2019-12-13","arxiv_id":"1912.06615","repositories_listed":0,"syntology":null},{"url":null,"slug":"provably-efficient-reinforcement-learning-1","title":"Provably Efficient Reinforcement Learning with Aggregated States","date":"2019-12-13","arxiv_id":"1912.06366","repositories_listed":0,"syntology":null},{"url":null,"slug":"recruitment-imitation-mechanism-for","title":"Recruitment-imitation Mechanism for Evolutionary Reinforcement Learning","date":"2019-12-13","arxiv_id":"1912.06310","repositories_listed":0,"syntology":null},{"url":null,"slug":"control-tutored-reinforcement-learning","title":"Control-Tutored Reinforcement Learning","date":"2019-12-12","arxiv_id":"1912.06085","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-activity-forecasting-for-generating","title":"Improved Activity Forecasting for Generating Trajectories","date":"2019-12-12","arxiv_id":"1912.05729","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-as-environment-a-deep-reinforcement","title":"Text as Environment: A Deep Reinforcement Learning Text Readability Assessment Model","date":"2019-12-12","arxiv_id":"1912.05957","repositories_listed":0,"syntology":null},{"url":null,"slug":"biases-for-emergent-communication-in-multi-1","title":"Biases for Emergent Communication in Multi-agent Reinforcement Learning","date":"2019-12-11","arxiv_id":"1912.05676","repositories_listed":0,"syntology":null},{"url":null,"slug":"doubly-robust-off-policy-actor-critic","title":"Doubly Robust Off-Policy Actor-Critic Algorithms for Reinforcement Learning","date":"2019-12-11","arxiv_id":"1912.05109","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-robotic-task-generalization-using","title":"Efficient Robotic Task Generalization Using Deep Model Fusion Reinforcement Learning","date":"2019-12-11","arxiv_id":"1912.05205","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-deep-reinforcement-learning-for","title":"Online Deep Reinforcement Learning for Autonomous UAV Navigation and Exploration of Outdoor Environments","date":"2019-12-11","arxiv_id":"1912.05684","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-and-robust-reinforcement-learning","title":"Efficient and Robust Reinforcement Learning with Uncertainty-based Value Expansion","date":"2019-12-10","arxiv_id":"1912.05328","repositories_listed":0,"syntology":null},{"url":null,"slug":"decentralized-multi-agent-reinforcement","title":"Decentralized Multi-Agent Reinforcement Learning with Networked Agents: Recent Advances","date":"2019-12-09","arxiv_id":"1912.03821","repositories_listed":0,"syntology":null},{"url":null,"slug":"intelligent-coordination-among-multiple","title":"Intelligent Coordination among Multiple Traffic Intersections Using Multi-Agent Reinforcement Learning","date":"2019-12-09","arxiv_id":"1912.03851","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-latent-state-spaces-for-planning-1","title":"Learning Latent State Spaces for Planning through Reward Prediction","date":"2019-12-09","arxiv_id":"1912.04201","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-sparse-representations-incrementally","title":"Learning Sparse Representations Incrementally in Deep Reinforcement Learning","date":"2019-12-09","arxiv_id":"1912.04002","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-code-coded-caching-via-deep","title":"Learning to Code: Coded Caching via Deep Reinforcement Learning","date":"2019-12-09","arxiv_id":"1912.04321","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimism-in-reinforcement-learning-with","title":"Optimism in Reinforcement Learning with Generalized Linear Function Approximation","date":"2019-12-09","arxiv_id":"1912.04136","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-based-reinforcement-learning-for","title":"Transformer Based Reinforcement Learning For Games","date":"2019-12-09","arxiv_id":"1912.03918","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-curricula-for-visual-meta-1","title":"Unsupervised Curricula for Visual Meta-Reinforcement Learning","date":"2019-12-09","arxiv_id":"1912.04226","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-reinforcement-learning-to-optimal","title":"From Reinforcement Learning to Optimal Control: A unified framework for sequential decisions","date":"2019-12-07","arxiv_id":"1912.03513","repositories_listed":0,"syntology":null},{"url":null,"slug":"no-regret-exploration-in-goal-oriented","title":"No-Regret Exploration in Goal-Oriented Reinforcement Learning","date":"2019-12-07","arxiv_id":"1912.03517","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-pedestrian-path-planning-model-in","title":"A pedestrian path-planning model in accordance with obstacle's danger with reinforcement learning","date":"2019-12-06","arxiv_id":"1912.02945","repositories_listed":0,"syntology":null},{"url":null,"slug":"alternative-function-approximation","title":"Alternative Function Approximation Parameterizations for Solving Games: An Analysis of $f$-Regression Counterfactual Regret Minimization","date":"2019-12-06","arxiv_id":"1912.02967","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-routing-a","title":"Deep Reinforcement Learning for Routing a Heterogeneous Fleet of Vehicles","date":"2019-12-06","arxiv_id":"1912.03341","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":"observational-overfitting-in-reinforcement-1","title":"Observational Overfitting in Reinforcement Learning","date":"2019-12-06","arxiv_id":"1912.02975","repositories_listed":0,"syntology":null},{"url":null,"slug":"191202552","title":"Reinforcement Learning with Non-Markovian Rewards","date":"2019-12-05","arxiv_id":"1912.02552","repositories_listed":0,"syntology":null}],"record_sha256":"994615976a7682cb00c288181e8aa2e6fb2ce446a5742f47ca2e7d5cfa420e39","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}