{"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/88","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":88,"pages_in_order":132,"rows_per_page":100,"rows":[8701,8800],"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/87","next":"/task/reinforcement-learning/papers/89","papers":[{"url":null,"slug":"reinforcement-learning-based-asymmetrical-dnn","title":"Reinforcement Learning Based Asymmetrical DNN Modularization for Optimal Loading","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-control-with","title":"Reinforcement Learning for Control with Probabilistic Stability Guarantee","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-with-bayesian","title":"Reinforcement Learning with Bayesian Classifiers: Efficient Skill Learning from Outcome Examples","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"representation-balancing-offline-model-based","title":"Representation Balancing Offline Model-based Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"rmix-risk-sensitive-multi-agent-reinforcement","title":"RMIX: Risk-Sensitive Multi-Agent Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-imitation-via-decision-time-planning","title":"Robust Imitation via Decision-Time Planning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-multi-agent-reinforcement-learning","title":"Robust Multi-Agent Reinforcement Learning Driven by Correlated Equilibrium","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-offline-reinforcement-learning-from","title":"Robust Offline Reinforcement Learning from Low-Quality Data","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-bayesian-inverse-reinforcement","title":"Scalable Bayesian Inverse Reinforcement Learning by Auto-Encoding Reward","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"success-rate-targeted-reinforcement-learning","title":"Success-Rate Targeted Reinforcement Learning by Disorientation Penalty","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unbiased-learning-with-state-conditioned","title":"Unbiased learning with State-Conditioned Rewards in Adversarial Imitation Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-weighted-offline-reinforcement","title":"Uncertainty Weighted Offline Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-and-leveraging-causal-relations","title":"Understanding and Leveraging Causal Relations in Deep Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-active-pre-training-for","title":"Unsupervised Active Pre-Training for Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"updet-universal-multi-agent-rl-via-policy","title":"UPDeT: Universal Multi-agent RL via Policy Decoupling with Transformers","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-imitation-with-reinforcement-learning","title":"Visual Imitation with Reinforcement Learning using Recurrent Siamese Networks","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"what-are-the-statistical-limits-of-batch-rl","title":"What are the Statistical Limits of Batch RL with Linear Function Approximation?","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"when-is-generalizable-reinforcement-learning","title":"When Is Generalizable Reinforcement Learning Tractable?","date":"2021-01-01","arxiv_id":"2101.00300","repositories_listed":0,"syntology":null},{"url":null,"slug":"curriculum-based-deep-reinforcement-learning","title":"Curriculum-based Deep Reinforcement Learning for Quantum Control","date":"2020-12-31","arxiv_id":"2012.15427","repositories_listed":0,"syntology":null},{"url":null,"slug":"relational-deep-reinforcement-learning-for","title":"Relational Deep Reinforcement Learning for Routing in Wireless Networks","date":"2020-12-31","arxiv_id":"2012.15700","repositories_listed":0,"syntology":null},{"url":null,"slug":"toward-reliable-designs-of-data-driven","title":"Toward Reliable Designs of Data-Driven Reinforcement Learning Tracking Control for Euler-Lagrange Systems","date":"2020-12-31","arxiv_id":"2101.00068","repositories_listed":0,"syntology":null},{"url":null,"slug":"lispr-an-options-framework-for-policy-reuse","title":"LISPR: An Options Framework for Policy Reuse with Reinforcement Learning","date":"2020-12-29","arxiv_id":"2012.14942","repositories_listed":0,"syntology":null},{"url":null,"slug":"risk-sensitive-deep-rl-variance-constrained","title":"Risk-Sensitive Deep RL: Variance-Constrained Actor-Critic Provably Finds Globally Optimal Policy","date":"2020-12-28","arxiv_id":"2012.14098","repositories_listed":0,"syntology":null},{"url":null,"slug":"portfolio-optimization-with-2d-relative","title":"Portfolio Optimization with 2D Relative-Attentional Gated Transformer","date":"2020-12-27","arxiv_id":"2101.03138","repositories_listed":0,"syntology":null},{"url":null,"slug":"stability-certified-reinforcement-learning","title":"Stability-Certified Reinforcement Learning via Spectral Normalization","date":"2020-12-26","arxiv_id":"2012.13744","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-sample-efficient-episodic-control","title":"Towards sample-efficient episodic control with DAC-ML","date":"2020-12-26","arxiv_id":"2012.13779","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-continual-reinforcement-learning-a","title":"Towards Continual Reinforcement Learning: A Review and Perspectives","date":"2020-12-25","arxiv_id":"2012.13490","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-state-representation-dueling-network-for","title":"A State Representation Dueling Network for Deep Reinforcement Learning","date":"2020-12-24","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"assured-rl-reinforcement-learning-with-almost","title":"Assured RL: Reinforcement Learning with Almost Sure Constraints","date":"2020-12-24","arxiv_id":"2012.13036","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-vehicle-routing-problems-using","title":"Learning Vehicle Routing Problems using Policy Optimisation","date":"2020-12-24","arxiv_id":"2012.13269","repositories_listed":0,"syntology":null},{"url":null,"slug":"scc-an-efficient-deep-reinforcement-learning","title":"SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft II","date":"2020-12-24","arxiv_id":"2012.13169","repositories_listed":0,"syntology":null},{"url":null,"slug":"spotter-extending-symbolic-planning-operators","title":"SPOTTER: Extending Symbolic Planning Operators through Targeted Reinforcement Learning","date":"2020-12-24","arxiv_id":"2012.13037","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-deep-clustering-and","title":"Unsupervised deep clustering and reinforcement learning can accurately segment MRI brain tumors with very small training sets","date":"2020-12-24","arxiv_id":"2012.13321","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-deep-reinforcement-learning-for","title":"Scalable Deep Reinforcement Learning for Routing and Spectrum Access in Physical Layer","date":"2020-12-22","arxiv_id":"2012.11783","repositories_listed":0,"syntology":null},{"url":null,"slug":"mobile-robot-planner-with-low-cost-cameras","title":"Mobile Robot Planner with Low-cost Cameras Using Deep Reinforcement Learning","date":"2020-12-21","arxiv_id":"2012.11160","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-based-product-delivery","title":"Reinforcement Learning-based Product Delivery Frequency Control","date":"2020-12-20","arxiv_id":"2012.10858","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantum-reinforcement-learning-in-continuous","title":"Quantum reinforcement learning in continuous action space","date":"2020-12-19","arxiv_id":"2012.10711","repositories_listed":0,"syntology":null},{"url":null,"slug":"exact-reduction-of-huge-action-spaces-in","title":"Exact Reduction of Huge Action Spaces in General Reinforcement Learning","date":"2020-12-18","arxiv_id":"2012.10200","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-principles-of-embodied","title":"Hierarchical principles of embodied reinforcement learning: A review","date":"2020-12-18","arxiv_id":"2012.10147","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-test-case","title":"Reinforcement Learning for Test Case Prioritization","date":"2020-12-18","arxiv_id":"2012.11364","repositories_listed":0,"syntology":null},{"url":null,"slug":"curiosity-in-exploring-chemical-space","title":"Curiosity in exploring chemical space: Intrinsic rewards for deep molecular reinforcement learning","date":"2020-12-17","arxiv_id":"2012.11293","repositories_listed":0,"syntology":null},{"url":null,"slug":"interactive-question-clarification-in","title":"Interactive Question Clarification in Dialogue via Reinforcement Learning","date":"2020-12-17","arxiv_id":"2012.09411","repositories_listed":0,"syntology":null},{"url":null,"slug":"intrinsically-motivated-goal-conditioned","title":"Autotelic Agents with Intrinsically Motivated Goal-Conditioned Reinforcement Learning: a Short Survey","date":"2020-12-17","arxiv_id":"2012.09830","repositories_listed":0,"syntology":null},{"url":null,"slug":"magnet-multi-agent-graph-network-for-deep","title":"MAGNet: Multi-agent Graph Network for Deep Multi-agent Reinforcement Learning","date":"2020-12-17","arxiv_id":"2012.09762","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparative-evaluation-of-machine-learning","title":"A comparative evaluation of machine learning methods for robot navigation through human crowds","date":"2020-12-16","arxiv_id":"2012.08822","repositories_listed":0,"syntology":null},{"url":null,"slug":"batch-constrained-distributional","title":"Batch-Constrained Distributional Reinforcement Learning for Session-based Recommendation","date":"2020-12-16","arxiv_id":"2012.08984","repositories_listed":0,"syntology":null},{"url":null,"slug":"sample-efficient-reinforcement-learning-via-1","title":"Sample-Efficient Reinforcement Learning via Counterfactual-Based Data Augmentation","date":"2020-12-16","arxiv_id":"2012.09092","repositories_listed":0,"syntology":null},{"url":null,"slug":"gegelati-lightweight-artificial-intelligence","title":"Gegelati: Lightweight Artificial Intelligence through Generic and Evolvable Tangled Program Graphs","date":"2020-12-15","arxiv_id":"2012.08296","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-framework-for-efficient-robotic","title":"Learning Visual Robotic Control Efficiently with Contrastive Pre-training and Data Augmentation","date":"2020-12-14","arxiv_id":"2012.07975","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-reinforcement-learning-formulation-of-the","title":"A Reinforcement Learning Formulation of the Lyapunov Optimization: Application to Edge Computing Systems with Queue Stability","date":"2020-12-14","arxiv_id":"2012.07279","repositories_listed":0,"syntology":null},{"url":null,"slug":"active-hierarchical-imitation-and","title":"Active Hierarchical Imitation and Reinforcement Learning","date":"2020-12-14","arxiv_id":"2012.07330","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-source-code-summarization-via","title":"Automatic Source Code Summarization via Reinforcement Learning","date":"2020-12-14","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deploying-reinforcement-learning-in-water","title":"Deploying Reinforcement Learning in Water Transport","date":"2020-12-14","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"evading-web-application-firewalls-with","title":"Evading Web Application Firewalls with Reinforcement Learning","date":"2020-12-14","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exponential-lower-bounds-for-batch","title":"Exponential Lower Bounds for Batch Reinforcement Learning: Batch RL can be Exponentially Harder than Online RL","date":"2020-12-14","arxiv_id":"2012.08005","repositories_listed":0,"syntology":null},{"url":null,"slug":"learn-to-manage-portfolio-with-reinforcement","title":"Learn To Manage Portfolio With Reinforcement Learning","date":"2020-12-14","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learn-to-play-tetris-with-deep-reinforcement","title":"Learn to Play Tetris with Deep Reinforcement Learning","date":"2020-12-14","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mobile-robots-autonomous-exploration-with","title":"Mobile Robots Autonomous Exploration with Reinforcement Learning","date":"2020-12-14","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mobile-robots-exploration-via-deep","title":"Mobile Robots Exploration via Deep Reinforcement Learning","date":"2020-12-14","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"optimal-portfolio-liquidation","title":"Optimal Portfolio Liquidation","date":"2020-12-14","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"portfolio-management-with-reinforcement","title":"Portfolio Management with Reinforcement Learning","date":"2020-12-14","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ranking-items-in-large-scale-item-search","title":"Ranking Items in Large-Scale Item Search Engines with Reinforcement Learning","date":"2020-12-14","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-based-character","title":"Reinforcement Learning Based Character Controlling","date":"2020-12-14","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-predict-optimize","title":"Reinforcement Learning for Predict+Optimize","date":"2020-12-14","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-the-beginning-of","title":"Reinforcement Learning for the Beginning of Starcraft II Game","date":"2020-12-14","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-in-20q-game-with","title":"Reinforcement Learning in 20Q Game with Generic Knowledge Bases","date":"2020-12-14","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-reinforcement-learning-with-stability","title":"Learning for MPC with Stability & Safety Guarantees","date":"2020-12-14","arxiv_id":"2012.07369","repositories_listed":0,"syntology":null},{"url":null,"slug":"sat-marl-specification-aware-training-in","title":"SAT-MARL: Specification Aware Training in Multi-Agent Reinforcement Learning","date":"2020-12-14","arxiv_id":"2012.07949","repositories_listed":0,"syntology":null},{"url":null,"slug":"train-a-snake-with-reinforcement-learning","title":"Train a snake with reinforcement learning algorithms","date":"2020-12-14","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"using-enhanced-gaussian-cross-entropy-in","title":"Using Enhanced Gaussian Cross-Entropy in Imitation Learning to Digging the First Diamond in Minecraft","date":"2020-12-14","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"virtual-autonomous-driving-with-reinforcement","title":"Virtual Autonomous Driving with Reinforcement Learning","date":"2020-12-14","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-with-subspaces-using","title":"Reinforcement Learning with Subspaces using Free Energy Paradigm","date":"2020-12-13","arxiv_id":"2012.07091","repositories_listed":0,"syntology":null},{"url":null,"slug":"noise-robust-end-to-end-quantum-control-using","title":"Noise-Robust End-to-End Quantum Control using Deep Autoregressive Policy Networks","date":"2020-12-12","arxiv_id":"2012.06701","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-reward-learning-for-offline","title":"Semi-supervised reward learning for offline reinforcement learning","date":"2020-12-12","arxiv_id":"2012.06899","repositories_listed":0,"syntology":null},{"url":null,"slug":"tutoring-reinforcement-learning-via-feedback","title":"Tutoring Reinforcement Learning via Feedback Control","date":"2020-12-12","arxiv_id":"2012.06863","repositories_listed":0,"syntology":null},{"url":null,"slug":"regularizing-action-policies-for-smooth","title":"Regularizing Action Policies for Smooth Control with Reinforcement Learning","date":"2020-12-11","arxiv_id":"2012.06644","repositories_listed":0,"syntology":null},{"url":null,"slug":"blending-mpc-value-function-approximation-for-1","title":"Blending MPC & Value Function Approximation for Efficient Reinforcement Learning","date":"2020-12-10","arxiv_id":"2012.05909","repositories_listed":0,"syntology":null},{"url":null,"slug":"flatland-rl-multi-agent-reinforcement","title":"Flatland-RL : Multi-Agent Reinforcement Learning on Trains","date":"2020-12-10","arxiv_id":"2012.05893","repositories_listed":0,"syntology":null},{"url":null,"slug":"performance-weighed-policy-sampling-for-meta","title":"Performance-Weighed Policy Sampling for Meta-Reinforcement Learning","date":"2020-12-10","arxiv_id":"2012.06016","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-agents-for-ubisoft-s","title":"Reinforcement Learning Agents for Ubisoft's Roller Champions","date":"2020-12-10","arxiv_id":"2012.06031","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-long-term","title":"Deep Reinforcement Learning for Long Term Hydropower Production Scheduling","date":"2020-12-09","arxiv_id":"2012.06312","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-stock","title":"Deep Reinforcement Learning for Stock Portfolio Optimization","date":"2020-12-09","arxiv_id":"2012.06325","repositories_listed":0,"syntology":null},{"url":null,"slug":"interactive-search-based-on-deep","title":"Interactive Search Based on Deep Reinforcement Learning","date":"2020-12-09","arxiv_id":"2012.06052","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-domain-randomised-reinforcement","title":"Robust Domain Randomised Reinforcement Learning through Peer-to-Peer Distillation","date":"2020-12-09","arxiv_id":"2012.04839","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-off-policy-reinforcement","title":"Semi-Supervised Off Policy Reinforcement Learning","date":"2020-12-09","arxiv_id":"2012.04809","repositories_listed":0,"syntology":null},{"url":null,"slug":"emergence-of-different-modes-of-tool-use-in-a","title":"Emergence of Different Modes of Tool Use in a Reaching and Dragging Task","date":"2020-12-08","arxiv_id":"2012.04700","repositories_listed":0,"syntology":null},{"url":null,"slug":"battery-model-calibration-with-deep","title":"Battery Model Calibration with Deep Reinforcement Learning","date":"2020-12-07","arxiv_id":"2012.04010","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-reservoir-management-through-deep","title":"Efficient Reservoir Management through Deep Reinforcement Learning","date":"2020-12-07","arxiv_id":"2012.03822","repositories_listed":0,"syntology":null},{"url":null,"slug":"vehicular-cooperative-perception-through","title":"Vehicular Cooperative Perception Through Action Branching and Federated Reinforcement Learning","date":"2020-12-07","arxiv_id":"2012.03414","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-navigation-based-on-deep","title":"Multi-agent navigation based on deep reinforcement learning and traditional pathfinding algorithm","date":"2020-12-05","arxiv_id":"2012.09134","repositories_listed":0,"syntology":null},{"url":null,"slug":"demonstration-efficient-inverse-reinforcement","title":"Demonstration-efficient Inverse Reinforcement Learning in Procedurally Generated Environments","date":"2020-12-04","arxiv_id":"2012.02527","repositories_listed":0,"syntology":null},{"url":"/paper/neural-dynamic-policies-for-end-to-end-1","slug":"neural-dynamic-policies-for-end-to-end-1","title":"Neural Dynamic Policies for End-to-End Sensorimotor Learning","date":"2020-12-04","arxiv_id":"2012.02788","repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-meta-level-model-based-reinforcement","title":"Offline Meta-level Model-based Reinforcement Learning Approach for Cold-Start Recommendation","date":"2020-12-04","arxiv_id":"2012.02476","repositories_listed":0,"syntology":null},{"url":null,"slug":"deepcrawl-deep-reinforcement-learning-for","title":"DeepCrawl: Deep Reinforcement Learning for Turn-based Strategy Games","date":"2020-12-03","arxiv_id":"2012.01914","repositories_listed":0,"syntology":null},{"url":null,"slug":"designing-a-prospective-covid-19-therapeutic","title":"Designing a Prospective COVID-19 Therapeutic with Reinforcement Learning","date":"2020-12-03","arxiv_id":"2012.01736","repositories_listed":0,"syntology":null},{"url":null,"slug":"partially-connected-automated-vehicle","title":"Partially Connected Automated Vehicle Cooperative Control Strategy with a Deep Reinforcement Learning Approach","date":"2020-12-03","arxiv_id":"2012.01841","repositories_listed":0,"syntology":null},{"url":null,"slug":"are-gradient-based-saliency-maps-useful-in","title":"Are Gradient-based Saliency Maps Useful in Deep Reinforcement Learning?","date":"2020-12-02","arxiv_id":"2012.01281","repositories_listed":0,"syntology":null},{"url":null,"slug":"driving-policy-adaptive-safeguard-for","title":"Driving-Policy Adaptive Safeguard for Autonomous Vehicles Using Reinforcement Learning","date":"2020-12-02","arxiv_id":"2012.01010","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-reinforcement-learning-for-antenna-tilt","title":"A Safe Reinforcement Learning Architecture for Antenna Tilt Optimisation","date":"2020-12-02","arxiv_id":"2012.01296","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-local-temporal-difference-code-for","title":"A Local Temporal Difference Code for Distributional Reinforcement Learning","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"e2c797eb962c94efbd37e24469393d3e1399e9a8db7ae0086c62558518d62e37","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}