{"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/papers/100","list_of":"/task/reinforcement-learning","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":100,"pages_in_order":132,"rows_per_page":100,"rows":[9901,10000],"of":13178,"counts":{"archive_papers_tagged":13178,"with_a_code_link":4183,"where_syntology_ran_a_sample":1175,"not_listed_spam_title":0,"listed":13178,"listed_where_code_ran":1175,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":988,"every_run_a_failure_of_syntologys_instrument":187,"listed_with_a_run_with_no_instrument_failure":988,"listed_every_run_a_failure_of_syntologys_instrument":187,"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","prev":"/task/reinforcement-learning/papers/99","next":"/task/reinforcement-learning/papers/101","papers":[{"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":"intra-variable-handwriting-inspection","title":"Intra-Variable Handwriting Inspection Reinforced with Idiosyncrasy Analysis","date":"2019-12-19","arxiv_id":"1912.12168","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":"relational-mimic-for-visual-adversarial","title":"Relational Mimic for Visual Adversarial Imitation Learning","date":"2019-12-18","arxiv_id":"1912.08444","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":"artificial-agents-learn-flexible-visual","title":"Learning Generalizable Visual Representations via Interactive Gameplay","date":"2019-12-17","arxiv_id":"1912.08195","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-bias-variance-tradeoff-textbooks-need","title":"On the Bias-Variance Tradeoff: Textbooks Need an Update","date":"2019-12-17","arxiv_id":"1912.08286","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":"complexity-of-stochastic-dual-dynamic","title":"Complexity of Stochastic Dual Dynamic Programming","date":"2019-12-16","arxiv_id":"1912.07702","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":"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":"adapting-behaviour-for-learning-progress-1","title":"Adapting Behaviour for Learning Progress","date":"2019-12-14","arxiv_id":"1912.06910","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":"long-term-planning-and-situational-awareness","title":"Long-Term Planning and Situational Awareness in OpenAI Five","date":"2019-12-13","arxiv_id":"1912.06721","repositories_listed":0,"syntology":null},{"url":null,"slug":"more-efficient-off-policy-evaluation-through","title":"More Efficient Off-Policy Evaluation through Regularized Targeted Learning","date":"2019-12-13","arxiv_id":"1912.06292","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":"provably-efficient-exploration-in-policy","title":"Provably Efficient Exploration in Policy Optimization","date":"2019-12-12","arxiv_id":"1912.05830","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":"energy-aware-scheduling-of-jobs-in","title":"Energy-aware Scheduling of Jobs in Heterogeneous Cluster Systems Using Deep Reinforcement Learning","date":"2019-12-11","arxiv_id":"1912.05160","repositories_listed":0,"syntology":null},{"url":null,"slug":"marginalized-state-distribution-entropy","title":"Marginalized State Distribution Entropy Regularization in Policy Optimization","date":"2019-12-11","arxiv_id":"1912.05128","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":"quality-of-syntactic-implication-of-rl-based","title":"Quality of syntactic implication of RL-based sentence summarization","date":"2019-12-11","arxiv_id":"1912.05493","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-can-learned-intrinsic-rewards-capture-1","title":"What Can Learned Intrinsic Rewards Capture?","date":"2019-12-11","arxiv_id":"1912.05500","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-finite-time-analysis-of-q-learning-with-1","title":"A Finite-Time Analysis of Q-Learning with Neural Network Function Approximation","date":"2019-12-10","arxiv_id":"1912.04511","repositories_listed":0,"syntology":null},{"url":null,"slug":"avid-learning-multi-stage-tasks-via-pixel","title":"AVID: Learning Multi-Stage Tasks via Pixel-Level Translation of Human Videos","date":"2019-12-10","arxiv_id":"1912.04443","repositories_listed":0,"syntology":null},{"url":null,"slug":"before-we-can-find-a-model-we-must-forget","title":"Before we can find a model, we must forget about perfection","date":"2019-12-10","arxiv_id":"1912.04964","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-bayesian-reward-learning-from","title":"Deep Bayesian Reward Learning from Preferences","date":"2019-12-10","arxiv_id":"1912.04472","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":"reducing-catastrophic-forgetting-in-modular","title":"Reducing Catastrophic Forgetting in Modular Neural Networks by Dynamic Information Balancing","date":"2019-12-10","arxiv_id":"1912.04508","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-recovery-of-agent-rewards-from","title":"Adversarial recovery of agent rewards from latent spaces of the limit order book","date":"2019-12-09","arxiv_id":"1912.04242","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":"deep-rl-based-trajectory-planning-for-aoi","title":"Deep RL-based Trajectory Planning for AoI Minimization in UAV-assisted IoT","date":"2019-12-09","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"grasping-in-the-wildlearning-6dof-closed-loop","title":"Grasping in the Wild:Learning 6DoF Closed-Loop Grasping from Low-Cost Demonstrations","date":"2019-12-09","arxiv_id":"1912.04344","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":"effects-of-a-social-force-model-reward-in","title":"Effects of a Social Force Model reward in Robot Navigation based on Deep Reinforcement Learning","date":"2019-12-08","arxiv_id":"1912.03747","repositories_listed":0,"syntology":null},{"url":null,"slug":"value-of-information-based-arbitration","title":"Value-of-Information based Arbitration between Model-based and Model-free Control","date":"2019-12-08","arxiv_id":"1912.05453","repositories_listed":0,"syntology":null},{"url":null,"slug":"driving-style-encoder-situational-reward","title":"Driving Style Encoder: Situational Reward Adaptation for General-Purpose Planning in Automated Driving","date":"2019-12-07","arxiv_id":"1912.03509","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":"making-smart-homes-smarter-optimizing-energy","title":"Making Smart Homes Smarter: Optimizing Energy Consumption with Human in the Loop","date":"2019-12-06","arxiv_id":"1912.03298","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":"risk-averse-trust-region-optimization-for","title":"Risk-Averse Trust Region Optimization for Reward-Volatility Reduction","date":"2019-12-06","arxiv_id":"1912.03193","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},{"url":null,"slug":"dynamic-pricing-on-e-commerce-platform-with","title":"Dynamic Pricing on E-commerce Platform with Deep Reinforcement Learning: A Field Experiment","date":"2019-12-05","arxiv_id":"1912.02572","repositories_listed":0,"syntology":null},{"url":null,"slug":"iterative-policy-space-expansion-in","title":"Iterative Policy-Space Expansion in Reinforcement Learning","date":"2019-12-05","arxiv_id":"1912.02532","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-run-a-power-network-challenge-for","title":"Learning to run a power network challenge for training topology controllers","date":"2019-12-05","arxiv_id":"1912.04211","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-with-convolutional","title":"Reinforcement Learning with Convolutional Reservoir Computing","date":"2019-12-05","arxiv_id":"1912.04161","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-reinforcement-learning-of-localized","title":"Scalable Reinforcement Learning for Multi-Agent Networked Systems","date":"2019-12-05","arxiv_id":"1912.02906","repositories_listed":0,"syntology":null},{"url":null,"slug":"algaedice-policy-gradient-from-arbitrary","title":"AlgaeDICE: Policy Gradient from Arbitrary Experience","date":"2019-12-04","arxiv_id":"1912.02074","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-model-compression-via-deep-reinforcement","title":"Deep Model Compression Via Two-Stage Deep Reinforcement Learning","date":"2019-12-04","arxiv_id":"1912.02254","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-efficient-representation-for","title":"Learning Efficient Representation for Intrinsic Motivation","date":"2019-12-04","arxiv_id":"1912.02624","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-norm-bounded-weighted-ambiguity","title":"Optimizing Norm-Bounded Weighted Ambiguity Sets for Robust MDPs","date":"2019-12-04","arxiv_id":"1912.02696","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-bandwidth","title":"Reinforcement learning for bandwidth estimation and congestion control in real-time communications","date":"2019-12-04","arxiv_id":"1912.02222","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-agent-communication-under-limited","title":"Learning Agent Communication under Limited Bandwidth by Message Pruning","date":"2019-12-03","arxiv_id":"1912.05304","repositories_listed":0,"syntology":null},{"url":null,"slug":"neighborhood-cognition-consistent-multi-agent","title":"Neighborhood Cognition Consistent Multi-Agent Reinforcement Learning","date":"2019-12-03","arxiv_id":"1912.01160","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-and-bandit-algorithms-for","title":"Online and Bandit Algorithms for Nonstationary Stochastic Saddle-Point Optimization","date":"2019-12-03","arxiv_id":"1912.01698","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-learned-formula-synthesis-in-set-theory","title":"Self-Learned Formula Synthesis in Set Theory","date":"2019-12-03","arxiv_id":"1912.01525","repositories_listed":0,"syntology":null},{"url":null,"slug":"191201715","title":"Human-Robot Collaboration via Deep Reinforcement Learning of Real-World Interactions","date":"2019-12-02","arxiv_id":"1912.01715","repositories_listed":0,"syntology":null},{"url":"/paper/degas-differentiable-efficient-generator","slug":"degas-differentiable-efficient-generator","title":"DEGAS: Differentiable Efficient Generator Search","date":"2019-12-02","arxiv_id":"1912.00606","repositories_listed":0,"syntology":null},{"url":null,"slug":"just-askan-interactive-learning-framework-for","title":"Just Ask:An Interactive Learning Framework for Vision and Language Navigation","date":"2019-12-02","arxiv_id":"1912.00915","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-policy-reinforcement-learning-with-entropy","title":"Policy Optimization Reinforcement Learning with Entropy Regularization","date":"2019-12-02","arxiv_id":"1912.01557","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-family-of-robust-stochastic-operators-for","title":"A Family of Robust Stochastic Operators for Reinforcement Learning","date":"2019-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"adversary-a3c-for-robust-reinforcement-1","title":"Adversary A3C for Robust Reinforcement Learning","date":"2019-12-01","arxiv_id":"1912.00330","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-smooth-non-convex-stochastic","title":"Efficient Smooth Non-Convex Stochastic Compositional Optimization via Stochastic Recursive Gradient Descent","date":"2019-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"explicit-planning-for-efficient-exploration","title":"Explicit Planning for Efficient Exploration in Reinforcement Learning","date":"2019-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"flow-rate-control-in-smart-district-heating","title":"Flow Rate Control in Smart District Heating Systems Using Deep Reinforcement Learning","date":"2019-12-01","arxiv_id":"1912.05313","repositories_listed":0,"syntology":null},{"url":null,"slug":"inverse-cognitive-radar-a-revealed","title":"Identifying Cognitive Radars -- Inverse Reinforcement Learning using Revealed Preferences","date":"2019-12-01","arxiv_id":"1912.00331","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-embedded-drl-for-intelligent-greenhouse","title":"Model Embedded DRL for Intelligent Greenhouse Control","date":"2019-12-01","arxiv_id":"1912.00020","repositories_listed":0,"syntology":null},{"url":null,"slug":"near-optimal-reinforcement-learning-in-2","title":"Near-Optimal Reinforcement Learning in Dynamic Treatment Regimes","date":"2019-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-temporal-difference-learning-converges-1","title":"Neural Temporal-Difference Learning Converges to Global Optima","date":"2019-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-trust-regionproximal-policy","title":"Neural Trust Region/Proximal Policy Optimization Attains Globally Optimal Policy","date":"2019-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"no-press-diplomacy-modeling-multi-agent-1","title":"No-Press Diplomacy: Modeling Multi-Agent Gameplay","date":"2019-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"optimization-for-reinforcement-learning-from","title":"Optimization for Reinforcement Learning: From Single Agent to Cooperative Agents","date":"2019-12-01","arxiv_id":"1912.00498","repositories_listed":0,"syntology":null},{"url":null,"slug":"provably-efficient-q-learning-with-function-1","title":"Provably Efficient Q-learning with Function Approximation via Distribution Shift Error Checking Oracle","date":"2019-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"provably-global-convergence-of-actor-critic-a","title":"Provably Global Convergence of Actor-Critic: A Case for Linear Quadratic Regulator with Ergodic Cost","date":"2019-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"66afc34a5b9253f025e98a4c5b76b26b2d1140f9f726adb2e8094e6d708468c6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}