{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/deep-reinforcement-learning/papers/40","list_of":"/task/deep-reinforcement-learning","task":"Deep Reinforcement Learning","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":40,"pages_in_order":59,"rows_per_page":100,"rows":[3901,4000],"of":5822,"counts":{"archive_papers_tagged":5822,"with_a_code_link":1739,"where_syntology_ran_a_sample":398,"not_listed_spam_title":0,"listed":5822,"listed_where_code_ran":398,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":340,"every_run_a_failure_of_syntologys_instrument":58,"listed_with_a_run_with_no_instrument_failure":340,"listed_every_run_a_failure_of_syntologys_instrument":58,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/deep-reinforcement-learning","prev":"/task/deep-reinforcement-learning/papers/39","next":"/task/deep-reinforcement-learning/papers/41","papers":[{"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":"can-an-ai-agent-hit-a-moving-target","title":"Can an AI agent hit a moving target?","date":"2021-10-06","arxiv_id":"2110.02474","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":"on-the-transferability-of-deep-q-networks","title":"On The Transferability of Deep-Q Networks","date":"2021-10-06","arxiv_id":"2110.02639","repositories_listed":0,"syntology":null},{"url":null,"slug":"pretraining-reinforcement-learning-sharpening","title":"Pretraining & Reinforcement Learning: Sharpening the Axe Before Cutting the Tree","date":"2021-10-06","arxiv_id":"2110.02497","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":"attaining-interpretability-in-reinforcement","title":"Hierarchical Primitive Composition: Simultaneous Activation of Skills with Inconsistent Action Dimensions in Multiple Hierarchies","date":"2021-10-05","arxiv_id":"2110.01833","repositories_listed":0,"syntology":null},{"url":null,"slug":"decentralized-cooperative-lane-changing-at","title":"Decentralized Cooperative Lane Changing at Freeway Weaving Areas Using Multi-Agent Deep Reinforcement Learning","date":"2021-10-05","arxiv_id":"2110.08124","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":"deepedge-a-deep-reinforcement-learning-based","title":"DeepEdge: A Deep Reinforcement Learning based Task Orchestrator for Edge Computing","date":"2021-10-05","arxiv_id":"2110.01863","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":"reinforcement-learning-with-real-time-docking","title":"Mining for Potent Inhibitors through Artificial Intelligence and Physics: A Unified Methodology for Ligand Based and Structure Based Drug Design","date":"2021-10-05","arxiv_id":"2110.01806","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":"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":"a-novel-automated-curriculum-strategy-to-1","title":"A Novel Automated Curriculum Strategy to Solve Hard Sokoban Planning Instances","date":"2021-10-03","arxiv_id":"2110.00898","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":"a-privacy-preserving-distributed-training","title":"A Privacy-preserving Distributed Training Framework for Cooperative Multi-agent Deep Reinforcement Learning","date":"2021-09-30","arxiv_id":"2109.14998","repositories_listed":0,"syntology":null},{"url":null,"slug":"bitcoin-transaction-strategy-construction","title":"Bitcoin Transaction Strategy Construction Based on Deep Reinforcement Learning","date":"2021-09-30","arxiv_id":"2109.14789","repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-interactions-of-autonomous-vehicles","title":"Modeling Interactions of Autonomous Vehicles and Pedestrians with Deep Multi-Agent Reinforcement Learning for Collision Avoidance","date":"2021-09-30","arxiv_id":"2109.15266","repositories_listed":0,"syntology":null},{"url":null,"slug":"stability-constrained-reinforcement-learning","title":"Stability Constrained Reinforcement Learning for Real-Time Voltage Control","date":"2021-09-30","arxiv_id":"2109.14854","repositories_listed":0,"syntology":null},{"url":null,"slug":"trajectory-planning-with-deep-reinforcement","title":"Trajectory Planning with Deep Reinforcement Learning in High-Level Action Spaces","date":"2021-09-30","arxiv_id":"2110.00044","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-risk-sensitive-policy-gradient-method","title":"A Risk-Sensitive Policy Gradient Method","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"actor-critic-policy-optimization-in-a-large","title":"Actor-Critic Policy Optimization in a Large-Scale Imperfect-Information Game","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-style-transfer-for-robust-policy","title":"Adversarial Style Transfer for Robust Policy Optimization in Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"an-optics-controlling-environment-and","title":"An Optics Controlling Environment and Reinforcement Learning Benchmarks","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"assessing-deep-reinforcement-learning","title":"Assessing Deep Reinforcement Learning Policies via Natural Corruptions at the Edge of Imperceptibility","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"causaldyna-improving-generalization-of-dyna","title":"CausalDyna: Improving Generalization of Dyna-style Reinforcement Learning via Counterfactual-Based Data Augmentation","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"continuous-deep-q-learning-in-optimal-control","title":"Continuous Deep Q-Learning in Optimal Control Problems: Normalized Advantage Functions Analysis","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cooperative-task-offloading-and-block-mining","title":"Cooperative Task Offloading and Block Mining in Blockchain-based Edge Computing with Multi-agent Deep Reinforcement Learning","date":"2021-09-29","arxiv_id":"2109.14263","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-dynamic-attention-model-with-gate","title":"Deep Dynamic Attention Model with Gate Mechanism for Solving Time-dependent Vehicle Routing Problems","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-of-intrinsically-motivated","title":"Deep Learning of Intrinsically Motivated Options in the Arcade Learning Environment","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-equal-risk-1","title":"Deep Reinforcement Learning for Equal Risk Option Pricing and Hedging under Dynamic Expectile Risk Measures","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"detecting-worst-case-corruptions-via-loss","title":"Detecting Worst-case Corruptions via Loss Landscape Curvature in Deep Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-reinforcement-learning","title":"Efficient Reinforcement Learning Experimentation in PyTorch","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"experience-replay-more-when-it-s-a-key","title":"Experience Replay More When It's a Key Transition in Deep Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"formulation-and-validation-of-a-car-following","title":"Formulation and validation of a car-following model based on deep reinforcement learning","date":"2021-09-29","arxiv_id":"2109.14268","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalizing-successor-features-to-continuous","title":"Generalizing Successor Features to continuous domains for Multi-task Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-safety-in-deep-reinforcement","title":"Improving Safety in Deep Reinforcement Learning using Unsupervised Action Planning","date":"2021-09-29","arxiv_id":"2109.14325","repositories_listed":0,"syntology":null},{"url":null,"slug":"information-bottleneck-based-behavior","title":"Information-Bottleneck-Based Behavior Representation Learning for Multi-agent Reinforcement learning","date":"2021-09-29","arxiv_id":"2109.14188","repositories_listed":0,"syntology":null},{"url":null,"slug":"interpreting-reinforcement-policies-through","title":"Interpreting Reinforcement Policies through Local Behaviors","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-controllable-elements-oriented","title":"Learning Controllable Elements Oriented Representations for Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"marnet-backdoor-attacks-against-value","title":"MARNET: Backdoor Attacks against Value-Decomposition Multi-Agent Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"maximizing-ensemble-diversity-in-deep","title":"Maximizing Ensemble Diversity in Deep Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigation-of-adversarial-policy-imitation","title":"Mitigation of Adversarial Policy Imitation via Constrained Randomization of Policy (CRoP)","date":"2021-09-29","arxiv_id":"2109.14678","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-batch-reinforcement-learning-via-sample","title":"Multi-batch Reinforcement Learning via Sample Transfer and Imitation Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-benefits-of-deep-rl-in-accelerated-mri","title":"On the benefits of deep RL in accelerated MRI sampling","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"p4o-efficient-deep-reinforcement-learning","title":"P4O: Efficient Deep Reinforcement Learning with Predictive Processing Proximal Policy Optimization","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/particle-based-stochastic-policy-optimization","slug":"particle-based-stochastic-policy-optimization","title":"Particle Based Stochastic Policy Optimization","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"pdqn-a-deep-reinforcement-learning-method-for","title":"PDQN - A Deep Reinforcement Learning Method for Planning with Long Delays: Optimization of Manufacturing Dispatching","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"programmatic-reinforcement-learning-without","title":"Programmatic Reinforcement Learning without Oracles","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-with-predictive","title":"Reinforcement Learning with Predictive Consistent Representations","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reward-shifting-for-optimistic-exploration","title":"Reward Shifting for Optimistic Exploration and Conservative Exploitation","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-structured-representations","title":"Self-Supervised Structured Representations for Deep Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"symmetric-machine-theory-of-mind","title":"Symmetric Machine Theory of Mind","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"task-driven-discovery-of-perceptual-schemas","title":"Task-driven Discovery of Perceptual Schemas for Generalization in Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"that-escalated-quickly-compounding-complexity","title":"That Escalated Quickly: Compounding Complexity by Editing Levels at the Frontier of Agent Capabilities","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-remarkable-effectiveness-of-combining","title":"The Remarkable Effectiveness of Combining Policy and Value Networks in A*-based Deep RL for AI Planning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-unknown-aware-deep-q-learning","title":"Towards Unknown-aware Deep Q-Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-the-generalization-gap-in","title":"Understanding the Generalization Gap in Visual Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"variance-reduced-domain-randomization-for","title":"Variance Reduced Domain Randomization for Policy Gradient","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"variational-oracle-guiding-for-reinforcement","title":"Variational oracle guiding for reinforcement learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"wavecorr-deep-reinforcement-learning-with","title":"WaveCorr: Deep Reinforcement Learning with Permutation Invariant Policy Networks for Portfolio Management","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"why-should-i-trust-you-bellman-evaluating-the","title":"Why Should I Trust You, Bellman? Evaluating the Bellman Objective with Off-Policy Data","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-informative-path-planning-using-deep","title":"Adaptive Informative Path Planning Using Deep Reinforcement Learning for UAV-based Active Sensing","date":"2021-09-28","arxiv_id":"2109.13570","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-offline-deep-reinforcement-learning-for","title":"An Offline Deep Reinforcement Learning for Maintenance Decision-Making","date":"2021-09-28","arxiv_id":"2109.15050","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-versus-evolution","title":"Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey","date":"2021-09-28","arxiv_id":"2110.01411","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-with-adjustments","title":"Deep Reinforcement Learning with Adjustments","date":"2021-09-28","arxiv_id":"2109.13463","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-more-when-it-needs-in-deep","title":"Exploring More When It Needs in Deep Reinforcement Learning","date":"2021-09-28","arxiv_id":"2109.13477","repositories_listed":0,"syntology":null},{"url":null,"slug":"identifying-reasoning-flaws-in-planning-based","title":"Identifying Reasoning Flaws in Planning-Based RL Using Tree Explanations","date":"2021-09-28","arxiv_id":"2109.13978","repositories_listed":0,"syntology":null},{"url":null,"slug":"longitudinal-deep-truck-deep-learning-and","title":"Longitudinal Deep Truck: Deep learning and deep reinforcement learning for modeling and control of longitudinal dynamics of heavy duty trucks","date":"2021-09-28","arxiv_id":"2109.14019","repositories_listed":0,"syntology":null},{"url":null,"slug":"drl-based-slice-placement-under-realistic","title":"DRL-based Slice Placement under Realistic Network Load Conditions","date":"2021-09-27","arxiv_id":"2109.12857","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficiently-training-on-policy-actor-critic","title":"Efficiently Training On-Policy Actor-Critic Networks in Robotic Deep Reinforcement Learning with Demonstration-like Sampled Exploration","date":"2021-09-27","arxiv_id":"2109.13005","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-wireless-3","title":"Deep Reinforcement Learning for Wireless Scheduling in Distributed Networked Control","date":"2021-09-26","arxiv_id":"2109.12562","repositories_listed":0,"syntology":null},{"url":null,"slug":"finite-state-machine-policies-modulating","title":"PM-FSM: Policies Modulating Finite State Machine for Robust Quadrupedal Locomotion","date":"2021-09-26","arxiv_id":"2109.12696","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-graph-policy-network-approach-for-volt-var","title":"A Graph Policy Network Approach for Volt-Var Control in Power Distribution Systems","date":"2021-09-24","arxiv_id":"2109.12073","repositories_listed":0,"syntology":null},{"url":null,"slug":"combing-policy-evaluation-and-policy","title":"The $f$-Divergence Reinforcement Learning Framework","date":"2021-09-24","arxiv_id":"2109.11867","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributed-deep-reinforcement-learning-for-5","title":"Combining Contention-Based Spectrum Access and Adaptive Modulation using Deep Reinforcement Learning","date":"2021-09-24","arxiv_id":"2109.11723","repositories_listed":0,"syntology":null},{"url":null,"slug":"learnable-triangulation-for-deep-learning","title":"Learnable Triangulation for Deep Learning-based 3D Reconstruction of Objects of Arbitrary Topology from Single RGB Images","date":"2021-09-24","arxiv_id":"2109.11844","repositories_listed":0,"syntology":null},{"url":null,"slug":"neuroprospecting-with-deeprl-agents","title":"Neuroprospecting with DeepRL agents","date":"2021-09-24","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multi-agent-deep-reinforcement-learning-2","title":"A Multi-Agent Deep Reinforcement Learning Coordination Framework for Connected and Automated Vehicles at Merging Roadways","date":"2021-09-23","arxiv_id":"2109.11672","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarialuscator-an-adversarial-drl-based","title":"ADVERSARIALuscator: An Adversarial-DRL Based Obfuscator and Metamorphic Malware SwarmGenerator","date":"2021-09-23","arxiv_id":"2109.11542","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-based-path-planning-for-long-range","title":"Deep Reinforcement Learning-Based Long-Range Autonomous Valet Parking for Smart Cities","date":"2021-09-23","arxiv_id":"2109.11661","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-training-blocks-generalization-in","title":"Adversarial Training Blocks Generalization in Neural Policies","date":"2021-09-22","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-lane-changing-decision-making","title":"Benchmarking Lane-changing Decision-making for Deep Reinforcement Learning","date":"2021-09-22","arxiv_id":"2109.10490","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-robust-agents-for-visual-navigation","title":"Benchmarking Augmentation Methods for Learning Robust Navigation Agents: the Winning Entry of the 2021 iGibson Challenge","date":"2021-09-22","arxiv_id":"2109.10493","repositories_listed":0,"syntology":null},{"url":null,"slug":"mepg-a-minimalist-ensemble-policy-gradient","title":"MEPG: A Minimalist Ensemble Policy Gradient Framework for Deep Reinforcement Learning","date":"2021-09-22","arxiv_id":"2109.10552","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimal-operation-of-a-hydrogen-based","title":"Optimal Operation of a Hydrogen-based Building Multi-Energy System Based on Deep Reinforcement Learning","date":"2021-09-22","arxiv_id":"2109.10754","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-multi-agent-reinforcement-learning-1","title":"Towards Multi-Agent Reinforcement Learning using Quantum Boltzmann Machines","date":"2021-09-22","arxiv_id":"2109.10900","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-simple-unified-framework-for-anomaly","title":"A Distance-based Anomaly Detection Framework for Deep Reinforcement Learning","date":"2021-09-21","arxiv_id":"2109.09889","repositories_listed":0,"syntology":null},{"url":null,"slug":"carl-lead-lidar-based-end-to-end-autonomous","title":"Carl-Lead: Lidar-based End-to-End Autonomous Driving with Contrastive Deep Reinforcement Learning","date":"2021-09-17","arxiv_id":"2109.08473","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-based-2","title":"Deep Reinforcement Learning Based Multidimensional Resource Management for Energy Harvesting Cognitive NOMA Communications","date":"2021-09-17","arxiv_id":"2109.09503","repositories_listed":0,"syntology":null},{"url":null,"slug":"integrating-deep-reinforcement-and-supervised","title":"Integrating Deep Reinforcement and Supervised Learning to Expedite Indoor Mapping","date":"2021-09-17","arxiv_id":"2109.08490","repositories_listed":0,"syntology":null},{"url":null,"slug":"rapid-rl-a-reconfigurable-architecture-with","title":"RAPID-RL: A Reconfigurable Architecture with Preemptive-Exits for Efficient Deep-Reinforcement Learning","date":"2021-09-16","arxiv_id":"2109.08231","repositories_listed":0,"syntology":null},{"url":null,"slug":"target-languages-vs-inductive-biases-for","title":"Target Languages (vs. Inductive Biases) for Learning to Act and Plan","date":"2021-09-15","arxiv_id":"2109.07195","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-hierarchical-reinforcement-agents-for","title":"Deep hierarchical reinforcement agents for automated penetration testing","date":"2021-09-14","arxiv_id":"2109.06449","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploration-in-deep-reinforcement-learning-a","title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain","date":"2021-09-14","arxiv_id":"2109.06668","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-practical-adversarial-attack-on-contingency","title":"A Practical Adversarial Attack on Contingency Detection of Smart Energy Systems","date":"2021-09-13","arxiv_id":"2109.06358","repositories_listed":0,"syntology":null}],"record_sha256":"a962b0455d4e229199c3576454747476cfef09bf96282a914e05238cb5277d42","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}