{"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/79","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":79,"pages_in_order":132,"rows_per_page":100,"rows":[7801,7900],"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/78","next":"/task/reinforcement-learning/papers/80","papers":[{"url":null,"slug":"investigation-of-independent-reinforcement","title":"Investigation of Independent Reinforcement Learning Algorithms in Multi-Agent Environments","date":"2021-11-01","arxiv_id":"2111.01100","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-operate-an-electric-vehicle","title":"Learning to Operate an Electric Vehicle Charging Station Considering Vehicle-grid Integration","date":"2021-11-01","arxiv_id":"2111.01294","repositories_listed":0,"syntology":null},{"url":null,"slug":"settling-the-horizon-dependence-of-sample","title":"Settling the Horizon-Dependence of Sample Complexity in Reinforcement Learning","date":"2021-11-01","arxiv_id":"2111.00633","repositories_listed":0,"syntology":null},{"url":null,"slug":"decentralized-multi-agent-reinforcement-3","title":"Decentralized Multi-Agent Reinforcement Learning: An Off-Policy Method","date":"2021-10-31","arxiv_id":"2111.00438","repositories_listed":0,"syntology":null},{"url":null,"slug":"adjacency-constraint-for-efficient","title":"Adjacency constraint for efficient hierarchical reinforcement learning","date":"2021-10-30","arxiv_id":"2111.00213","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-discretization-in-online","title":"Adaptive Discretization in Online Reinforcement Learning","date":"2021-10-29","arxiv_id":"2110.15843","repositories_listed":0,"syntology":null},{"url":null,"slug":"brick-by-brick-combinatorial-construction","title":"Brick-by-Brick: Combinatorial Construction with Deep Reinforcement Learning","date":"2021-10-29","arxiv_id":"2110.15481","repositories_listed":0,"syntology":null},{"url":null,"slug":"mixed-cooperative-competitive-communication","title":"Mixed Cooperative-Competitive Communication Using Multi-Agent Reinforcement Learning","date":"2021-10-29","arxiv_id":"2110.15762","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerating-robotic-reinforcement-learning","title":"Accelerating Robotic Reinforcement Learning via Parameterized Action Primitives","date":"2021-10-28","arxiv_id":"2110.15360","repositories_listed":0,"syntology":null},{"url":null,"slug":"d2rlir-an-improved-and-diversified-ranking","title":"D2RLIR : an improved and diversified ranking function in interactive recommendation systems based on deep reinforcement learning","date":"2021-10-28","arxiv_id":"2110.15089","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-law-of-iterated-logarithm-for-multi-agent","title":"A Law of Iterated Logarithm for Multi-Agent Reinforcement Learning","date":"2021-10-27","arxiv_id":"2110.15092","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparing-heuristics-constraint-optimization","title":"Comparing Heuristics, Constraint Optimization, and Reinforcement Learning for an Industrial 2D Packing Problem","date":"2021-10-27","arxiv_id":"2110.14535","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-based-multi-agent-reinforcement-1","title":"Model based Multi-agent Reinforcement Learning with Tensor Decompositions","date":"2021-10-27","arxiv_id":"2110.14524","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-in-factored-action","title":"Reinforcement Learning in Factored Action Spaces using Tensor Decompositions","date":"2021-10-27","arxiv_id":"2110.14538","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-in-linear-mdps","title":"Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection","date":"2021-10-27","arxiv_id":"2110.14798","repositories_listed":0,"syntology":null},{"url":null,"slug":"transfer-learning-with-causal-counterfactual","title":"Transfer learning with causal counterfactual reasoning in Decision Transformers","date":"2021-10-27","arxiv_id":"2110.14355","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-dpdk-based-acceleration-method-for","title":"Accelerating Distributed Deep Reinforcement Learning by In-Network Experience Sampling","date":"2021-10-26","arxiv_id":"2110.13506","repositories_listed":0,"syntology":null},{"url":null,"slug":"applications-of-multi-agent-reinforcement","title":"Applications of Multi-Agent Reinforcement Learning in Future Internet: A Comprehensive Survey","date":"2021-10-26","arxiv_id":"2110.13484","repositories_listed":0,"syntology":null},{"url":null,"slug":"automating-control-of-overestimation-bias-for","title":"Automating Control of Overestimation Bias for Reinforcement Learning","date":"2021-10-26","arxiv_id":"2110.13523","repositories_listed":0,"syntology":null},{"url":null,"slug":"entrpo-trust-region-policy-optimization","title":"EnTRPO: Trust Region Policy Optimization Method with Entropy Regularization","date":"2021-10-26","arxiv_id":"2110.13373","repositories_listed":0,"syntology":null},{"url":null,"slug":"hinge-policy-optimization-rethinking-policy-1","title":"Neural PPO-Clip Attains Global Optimality: A Hinge Loss Perspective","date":"2021-10-26","arxiv_id":"2110.13799","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-reinforcement-learning-approach-for-9","title":"A Deep Reinforcement Learning Approach for Audio-based Navigation and Audio Source Localization in Multi-speaker Environments","date":"2021-10-25","arxiv_id":"2110.12778","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-q-learning-be-improved-with-advice","title":"Can Q-Learning be Improved with Advice?","date":"2021-10-25","arxiv_id":"2110.13052","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-domain-adaptation-with-dynamics","title":"Unsupervised Domain Adaptation with Dynamics-Aware Rewards in Reinforcement Learning","date":"2021-10-25","arxiv_id":"2110.12997","repositories_listed":0,"syntology":null},{"url":null,"slug":"foresight-of-graph-reinforcement-learning","title":"Foresight of Graph Reinforcement Learning Latent Permutations Learnt by Gumbel Sinkhorn Network","date":"2021-10-23","arxiv_id":"2110.12144","repositories_listed":0,"syntology":null},{"url":null,"slug":"fully-distributed-actor-critic-architecture","title":"Fully Distributed Actor-Critic Architecture for Multitask Deep Reinforcement Learning","date":"2021-10-23","arxiv_id":"2110.12306","repositories_listed":0,"syntology":null},{"url":null,"slug":"off-policy-reinforcement-learning-with-2","title":"Off-policy Reinforcement Learning with Optimistic Exploration and Distribution Correction","date":"2021-10-22","arxiv_id":"2110.12081","repositories_listed":0,"syntology":null},{"url":null,"slug":"patient-level-simulation-and-reinforcement","title":"Patient level simulation and reinforcement learning to discover novel strategies for treating ovarian cancer","date":"2021-10-22","arxiv_id":"2110.11872","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-process-control","title":"Reinforcement Learning for Process Control with Application in Semiconductor Manufacturing","date":"2021-10-22","arxiv_id":"2110.11572","repositories_listed":0,"syntology":null},{"url":null,"slug":"anti-concentrated-confidence-bonuses-for-1","title":"Anti-Concentrated Confidence Bonuses for Scalable Exploration","date":"2021-10-21","arxiv_id":"2110.11202","repositories_listed":0,"syntology":null},{"url":null,"slug":"neuro-symbolic-reinforcement-learning-with","title":"Neuro-Symbolic Reinforcement Learning with First-Order Logic","date":"2021-10-21","arxiv_id":"2110.10963","repositories_listed":0,"syntology":null},{"url":null,"slug":"off-dynamics-inverse-reinforcement-learning","title":"Off-Dynamics Inverse Reinforcement Learning from Hetero-Domain","date":"2021-10-21","arxiv_id":"2110.11443","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-based-optimal-camera","title":"Reinforcement Learning Based Optimal Camera Placement for Depth Observation of Indoor Scenes","date":"2021-10-21","arxiv_id":"2110.11106","repositories_listed":0,"syntology":null},{"url":null,"slug":"computationally-efficient-safe-reinforcement","title":"Computationally Efficient Safe Reinforcement Learning for Power Systems","date":"2021-10-20","arxiv_id":"2110.10333","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributed-reinforcement-learning-for-3","title":"Distributed Reinforcement Learning for Privacy-Preserving Dynamic Edge Caching","date":"2021-10-20","arxiv_id":"2110.10349","repositories_listed":0,"syntology":null},{"url":null,"slug":"feedback-linearization-of-car-dynamics-for","title":"Feedback Linearization of Car Dynamics for Racing via Reinforcement Learning","date":"2021-10-20","arxiv_id":"2110.10441","repositories_listed":0,"syntology":null},{"url":null,"slug":"more-efficient-exploration-with-symbolic","title":"More Efficient Exploration with Symbolic Priors on Action Sequence Equivalences","date":"2021-10-20","arxiv_id":"2110.10632","repositories_listed":0,"syntology":null},{"url":null,"slug":"transferring-reinforcement-learning-for-dc-dc","title":"Transferring Reinforcement Learning for DC-DC Buck Converter Control via Duty Ratio Mapping: From Simulation to Implementation","date":"2021-10-20","arxiv_id":"2110.10490","repositories_listed":0,"syntology":null},{"url":null,"slug":"aesthetic-photo-collage-with-deep","title":"Aesthetic Photo Collage with Deep Reinforcement Learning","date":"2021-10-19","arxiv_id":"2110.09775","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-cooperation-by-balancing-exploration","title":"Improved cooperation by balancing exploration and exploitation in intertemporal social dilemma tasks","date":"2021-10-19","arxiv_id":"2111.09152","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-robotic-manipulation-skills-using-an","title":"Learning Robotic Manipulation Skills Using an Adaptive Force-Impedance Action Space","date":"2021-10-19","arxiv_id":"2110.09904","repositories_listed":0,"syntology":null},{"url":null,"slug":"state-based-episodic-memory-for-multi-agent","title":"State-based Episodic Memory for Multi-Agent Reinforcement Learning","date":"2021-10-19","arxiv_id":"2110.09817","repositories_listed":0,"syntology":null},{"url":null,"slug":"embracing-advanced-ai-ml-to-help-investors","title":"Embracing advanced AI/ML to help investors achieve success: Vanguard Reinforcement Learning for Financial Goal Planning","date":"2021-10-18","arxiv_id":"2110.12003","repositories_listed":0,"syntology":null},{"url":null,"slug":"provable-hierarchy-based-meta-reinforcement-1","title":"Provable Hierarchy-Based Meta-Reinforcement Learning","date":"2021-10-18","arxiv_id":"2110.09507","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-based-coverage-path","title":"Reinforcement Learning-Based Coverage Path Planning with Implicit Cellular Decomposition","date":"2021-10-18","arxiv_id":"2110.09018","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-instance-optimal-offline","title":"Towards Instance-Optimal Offline Reinforcement Learning with Pessimism","date":"2021-10-17","arxiv_id":"2110.08695","repositories_listed":0,"syntology":null},{"url":null,"slug":"case-based-reasoning-for-better-1","title":"Case-based Reasoning for Better Generalization in Textual Reinforcement Learning","date":"2021-10-16","arxiv_id":"2110.08470","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-network-pruning-through-constrained","title":"Neural Network Pruning Through Constrained Reinforcement Learning","date":"2021-10-16","arxiv_id":"2110.08558","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-broad-persistent-advising-approach-for-deep","title":"A Broad-persistent Advising Approach for Deep Interactive Reinforcement Learning in Robotic Environments","date":"2021-10-15","arxiv_id":"2110.08003","repositories_listed":0,"syntology":null},{"url":null,"slug":"containerized-distributed-value-based-multi-1","title":"Containerized Distributed Value-Based Multi-Agent Reinforcement Learning","date":"2021-10-15","arxiv_id":"2110.08169","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-probabilistic-logic-models-for","title":"Dynamic probabilistic logic models for effective abstractions in RL","date":"2021-10-15","arxiv_id":"2110.08318","repositories_listed":0,"syntology":null},{"url":null,"slug":"effects-of-different-optimization","title":"Effects of Different Optimization Formulations in Evolutionary Reinforcement Learning on Diverse Behavior Generation","date":"2021-10-15","arxiv_id":"2110.08122","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-hyperparameter-optimization-by-1","title":"Improving Hyperparameter Optimization by Planning Ahead","date":"2021-10-15","arxiv_id":"2110.08028","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-policy-model-errors-in-reinforcement-1","title":"On-Policy Model Errors in Reinforcement Learning","date":"2021-10-15","arxiv_id":"2110.07985","repositories_listed":0,"syntology":null},{"url":null,"slug":"wasserstein-unsupervised-reinforcement","title":"Wasserstein Unsupervised Reinforcement Learning","date":"2021-10-15","arxiv_id":"2110.07940","repositories_listed":0,"syntology":null},{"url":null,"slug":"haven-hierarchical-cooperative-multi-agent","title":"HAVEN: Hierarchical Cooperative Multi-Agent Reinforcement Learning with Dual Coordination Mechanism","date":"2021-10-14","arxiv_id":"2110.07246","repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-reinforcement-learning-with-soft","title":"Offline Reinforcement Learning with Soft Behavior Regularization","date":"2021-10-14","arxiv_id":"2110.07395","repositories_listed":0,"syntology":null},{"url":null,"slug":"provably-efficient-multi-agent-reinforcement","title":"Provably Efficient Multi-Agent Reinforcement Learning with Fully Decentralized Communication","date":"2021-10-14","arxiv_id":"2110.07392","repositories_listed":0,"syntology":null},{"url":null,"slug":"block-contextual-mdps-for-continual-learning-1","title":"Block Contextual MDPs for Continual Learning","date":"2021-10-13","arxiv_id":"2110.06972","repositories_listed":0,"syntology":null},{"url":null,"slug":"feudal-reinforcement-learning-by-reading-1","title":"Feudal Reinforcement Learning by Reading Manuals","date":"2021-10-13","arxiv_id":"2110.06477","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-standards-design","title":"Reinforcement Learning for Standards Design","date":"2021-10-13","arxiv_id":"2110.06909","repositories_listed":0,"syntology":null},{"url":null,"slug":"gridlearn-multiagent-reinforcement-learning","title":"GridLearn: Multiagent Reinforcement Learning for Grid-Aware Building Energy Management","date":"2021-10-12","arxiv_id":"2110.06396","repositories_listed":0,"syntology":null},{"url":null,"slug":"provably-efficient-reinforcement-learning-in","title":"Provably Efficient Reinforcement Learning in Decentralized General-Sum Markov Games","date":"2021-10-12","arxiv_id":"2110.05682","repositories_listed":0,"syntology":null},{"url":null,"slug":"reward-free-model-based-reinforcement","title":"Reward-Free Model-Based Reinforcement Learning with Linear Function Approximation","date":"2021-10-12","arxiv_id":"2110.06394","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-abstraction-in-reinforcement","title":"Temporal Abstraction in Reinforcement Learning with the Successor Representation","date":"2021-10-12","arxiv_id":"2110.05740","repositories_listed":0,"syntology":null},{"url":null,"slug":"bid-optimization-using-maximum-entropy","title":"Bid Optimization using Maximum Entropy Reinforcement Learning","date":"2021-10-11","arxiv_id":"2110.05032","repositories_listed":0,"syntology":null},{"url":null,"slug":"rein-2-giving-birth-to-prepared-reinforcement","title":"REIN-2: Giving Birth to Prepared Reinforcement Learning Agents Using Reinforcement Learning Agents","date":"2021-10-11","arxiv_id":"2110.05128","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-augmented-reality-platform-for-introducing","title":"An Augmented Reality Platform for Introducing Reinforcement Learning to K-12 Students with Robots","date":"2021-10-10","arxiv_id":"2110.04697","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-condition-multi-objective-optimization","title":"Multi-condition multi-objective optimization using deep reinforcement learning","date":"2021-10-10","arxiv_id":"2110.05945","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-systematic-fx","title":"Reinforcement Learning for Systematic FX Trading","date":"2021-10-10","arxiv_id":"2110.04745","repositories_listed":0,"syntology":null},{"url":null,"slug":"provably-efficient-black-box-action-poisoning","title":"Provably Efficient Black-Box Action Poisoning Attacks Against Reinforcement Learning","date":"2021-10-09","arxiv_id":"2110.04471","repositories_listed":0,"syntology":null},{"url":null,"slug":"cheerbots-chatbots-toward-empathy-and","title":"CheerBots: Chatbots toward Empathy and Emotionusing Reinforcement Learning","date":"2021-10-08","arxiv_id":"2110.03949","repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-design-choices-in-model-based","title":"Revisiting Design Choices in Offline Model-Based Reinforcement Learning","date":"2021-10-08","arxiv_id":"2110.04135","repositories_listed":0,"syntology":null},{"url":null,"slug":"showing-your-offline-reinforcement-learning","title":"Showing Your Offline Reinforcement Learning Work: Online Evaluation Budget Matters","date":"2021-10-08","arxiv_id":"2110.04156","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-model-selection-approach-for-corruption","title":"A Model Selection Approach for Corruption Robust Reinforcement Learning","date":"2021-10-07","arxiv_id":"2110.03580","repositories_listed":0,"syntology":null},{"url":null,"slug":"bad-policy-density-a-measure-of-reinforcement","title":"Bad-Policy Density: A Measure of Reinforcement Learning Hardness","date":"2021-10-07","arxiv_id":"2110.03424","repositories_listed":0,"syntology":null},{"url":null,"slug":"designing-composites-with-target-effective","title":"Designing Composites with Target Effective Young's Modulus using Reinforcement Learning","date":"2021-10-07","arxiv_id":"2110.05260","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-pessimism-for-robust-and-efficient","title":"Learning Pessimism for Robust and Efficient Off-Policy Reinforcement Learning","date":"2021-10-07","arxiv_id":"2110.03375","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-in-reward-mixing-mdps","title":"Reinforcement Learning in Reward-Mixing MDPs","date":"2021-10-07","arxiv_id":"2110.03743","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-control-of-a-mechatronic-system","title":"Adaptive control of a mechatronic system using constrained residual reinforcement learning","date":"2021-10-06","arxiv_id":"2110.02566","repositories_listed":0,"syntology":null},{"url":null,"slug":"heterogeneous-attentions-for-solving-pickup","title":"Heterogeneous Attentions for Solving Pickup and Delivery Problem via Deep Reinforcement Learning","date":"2021-10-06","arxiv_id":"2110.02634","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-generalization-of-deep","title":"Improving Generalization of Deep Reinforcement Learning-based TSP Solvers","date":"2021-10-06","arxiv_id":"2110.02843","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-reinforcement-learning-framework-for-4","title":"A Deep Reinforcement Learning Framework for Contention-Based Spectrum Sharing","date":"2021-10-05","arxiv_id":"2110.02736","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-guidewire","title":"Deep reinforcement learning for guidewire navigation in coronary artery phantom","date":"2021-10-05","arxiv_id":"2110.01840","repositories_listed":0,"syntology":null},{"url":null,"slug":"narle-natural-language-models-using","title":"NaRLE: Natural Language Models using Reinforcement Learning with Emotion Feedback","date":"2021-10-05","arxiv_id":"2110.02148","repositories_listed":0,"syntology":null},{"url":null,"slug":"ottr-off-road-trajectory-tracking-using","title":"OTTR: Off-Road Trajectory Tracking using Reinforcement Learning","date":"2021-10-05","arxiv_id":"2110.02332","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-modified-q-learning-algorithm-for-rate","title":"A Modified Q-Learning Algorithm for Rate-Profiling of Polarization Adjusted Convolutional (PAC) Codes","date":"2021-10-04","arxiv_id":"2110.01563","repositories_listed":0,"syntology":null},{"url":null,"slug":"automating-privilege-escalation-with-deep","title":"Automating Privilege Escalation with Deep Reinforcement Learning","date":"2021-10-04","arxiv_id":"2110.01362","repositories_listed":0,"syntology":null},{"url":null,"slug":"behaviour-conditioned-policies-for","title":"Behaviour-conditioned policies for cooperative reinforcement learning tasks","date":"2021-10-04","arxiv_id":"2110.01266","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-assist-agents-by-observing-them","title":"Learning to Assist Agents by Observing Them","date":"2021-10-04","arxiv_id":"2110.01311","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-path-planning-using-deep","title":"Multi-Agent Path Planning Using Deep Reinforcement Learning","date":"2021-10-04","arxiv_id":"2110.01460","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-admission-control-1","title":"Reinforcement Learning for Admission Control in Wireless Virtual Network Embedding","date":"2021-10-04","arxiv_id":"2110.01262","repositories_listed":0,"syntology":null},{"url":null,"slug":"decentralized-safe-reinforcement-learning-for","title":"Decentralized Safe Reinforcement Learning for Voltage Control","date":"2021-10-03","arxiv_id":"2110.01126","repositories_listed":0,"syntology":null},{"url":null,"slug":"drl-clusters-buffer-management-with","title":"DRL-Clusters: Buffer Management with Clustering based Deep Reinforcement Learning","date":"2021-10-03","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"parallel-actors-and-learners-a-framework-for","title":"Parallel Actors and Learners: A Framework for Generating Scalable RL Implementations","date":"2021-10-03","arxiv_id":"2110.01101","repositories_listed":0,"syntology":null},{"url":null,"slug":"feel-good-thompson-sampling-for-contextual","title":"Feel-Good Thompson Sampling for Contextual Bandits and Reinforcement Learning","date":"2021-10-02","arxiv_id":"2110.00871","repositories_listed":0,"syntology":null},{"url":null,"slug":"seeking-visual-discomfort-curiosity-driven","title":"Seeking Visual Discomfort: Curiosity-driven Representations for Reinforcement Learning","date":"2021-10-02","arxiv_id":"2110.00784","repositories_listed":0,"syntology":null},{"url":null,"slug":"cellular-traffic-offloading-via-opportunistic","title":"Cellular traffic offloading via Opportunistic Networking with Reinforcement Learning","date":"2021-10-01","arxiv_id":"2110.00397","repositories_listed":0,"syntology":null},{"url":null,"slug":"divergence-regularized-multi-agent-actor","title":"Divergence-Regularized Multi-Agent Actor-Critic","date":"2021-10-01","arxiv_id":"2110.00304","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-lane-cruising-using-hierarchical","title":"Multi-lane Cruising Using Hierarchical Planning and Reinforcement Learning","date":"2021-10-01","arxiv_id":"2110.00650","repositories_listed":0,"syntology":null}],"record_sha256":"ce75c51b606e69fb492ba846a3139c8e3fe38bb540b9e1232f7a4279e89b1766","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}