{"total":93,"rows":[{"id":"2102.02915","title":"How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned","created":"2021-02-04","cited_by_count":213,"area":null},{"id":"2103.06257","title":"Maximum Entropy RL (Provably) Solves Some Robust RL Problems","created":"2021-03-10","cited_by_count":176,"area":null},{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110,"area":null},{"id":"2207.00713","title":"q-Learning in Continuous Time","created":"2022-07-02","cited_by_count":91,"area":null},{"id":"2104.10159","title":"MBRL-Lib: A Modular Library for Model-based Reinforcement Learning","created":"2021-04-20","cited_by_count":42,"area":null},{"id":"2107.08285","title":"Greedification Operators for Policy Optimization: Investigating Forward and Reverse KL Divergences","created":"2021-07-17","cited_by_count":41,"area":null},{"id":"2312.10256","title":"Multi-agent Reinforcement Learning: A Comprehensive Survey","created":"2023-12-15","cited_by_count":33,"area":null},{"id":"2201.12417","title":"Why Should I Trust You, Bellman? The Bellman Error is a Poor Replacement for Value Error","created":"2022-01-28","cited_by_count":32,"area":null},{"id":"2110.10149","title":"Continuous Control with Action Quantization from Demonstrations","created":"2021-10-19","cited_by_count":22,"area":null},{"id":"2106.03050","title":"Efficient Continuous Control with Double Actors and Regularized Critics","created":"2021-06-06","cited_by_count":21,"area":null},{"id":"2107.10400","title":"Species Distribution Modeling for Machine Learning Practitioners: A Review","created":"2021-07-03","cited_by_count":21,"area":null},{"id":"2210.11481","title":"Improving aircraft performance using machine learning: a review","created":"2022-10-20","cited_by_count":19,"area":null},{"id":"2210.11931","title":"Deep Reinforcement Learning for Inverse Inorganic Materials Design","created":"2022-10-21","cited_by_count":19,"area":null},{"id":"2211.02147","title":"A Survey on Reinforcement Learning in Aviation Applications","created":"2022-11-03","cited_by_count":19,"area":null},{"id":"2212.00824","title":"On-device Training: A First Overview on Existing Systems","created":"2022-12-01","cited_by_count":19,"area":null},{"id":"2302.13960","title":"Acquisition Conditioned Oracle for Nongreedy Active Feature Acquisition","created":"2023-02-27","cited_by_count":19,"area":null},{"id":"2302.04903","title":"AdaptSim: Task-Driven Simulation Adaptation for Sim-to-Real Transfer","created":"2023-02-09","cited_by_count":18,"area":null},{"id":"2108.10273","title":"Collect & Infer -- a fresh look at data-efficient Reinforcement Learning","created":"2021-08-23","cited_by_count":17,"area":null},{"id":"2502.02705","title":"Rapidly Adapting Policies to the Real World via Simulation-Guided Fine-Tuning","created":"2025-02-04","cited_by_count":17,"area":null},{"id":"2108.07124","title":"Using Cyber Terrain in Reinforcement Learning for Penetration Testing","created":"2021-08-16","cited_by_count":16,"area":null},{"id":"2306.17750","title":"TD Convergence: An Optimization Perspective","created":"2023-06-30","cited_by_count":16,"area":null},{"id":"2103.12726","title":"Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning","created":"2021-03-23","cited_by_count":15,"area":null},{"id":"2103.17258","title":"Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning","created":"2021-03-31","cited_by_count":15,"area":null},{"id":"2212.09010","title":"Risk-Sensitive Reinforcement Learning with Exponential Criteria","created":"2022-12-18","cited_by_count":15,"area":null},{"id":"2301.00519","title":"Holistic Network Virtualization and Pervasive Network Intelligence for 6G","created":"2023-01-02","cited_by_count":14,"area":null},{"id":"2107.08241","title":"High-Accuracy Model-Based Reinforcement Learning, a Survey","created":"2021-07-17","cited_by_count":13,"area":null},{"id":"2211.06625","title":"CACTO: Continuous Actor-Critic with Trajectory Optimization -- Towards global optimality","created":"2022-11-12","cited_by_count":12,"area":null},{"id":"2110.04686","title":"Braxlines: Fast and Interactive Toolkit for RL-driven Behavior Engineering beyond Reward Maximization","created":"2021-10-10","cited_by_count":11,"area":null},{"id":"2110.10349","title":"Distributed Reinforcement Learning for Privacy-Preserving Dynamic Edge Caching","created":"2021-10-20","cited_by_count":10,"area":null},{"id":"2107.00140","title":"Applications of the Free Energy Principle to Machine Learning and Neuroscience","created":"2021-06-30","cited_by_count":9,"area":null},{"id":"2108.07041","title":"Implicitly Regularized RL with Implicit Q-Values","created":"2021-08-16","cited_by_count":9,"area":null},{"id":"2112.03798","title":"PTR-PPO: Proximal Policy Optimization with Prioritized Trajectory Replay","created":"2021-12-07","cited_by_count":9,"area":null},{"id":"2201.05000","title":"Automated Reinforcement Learning: An Overview","created":"2022-01-13","cited_by_count":9,"area":null},{"id":"2402.01344","title":"Monotone, Bi-Lipschitz, and Polyak-Lojasiewicz Networks","created":"2024-02-02","cited_by_count":9,"area":null},{"id":"2110.02414","title":"Imaginary Hindsight Experience Replay: Curious Model-based Learning for Sparse Reward Tasks","created":"2021-10-05","cited_by_count":8,"area":null},{"id":"2106.04075","title":"Multi-Agent Cooperative Bidding Games for Multi-Objective Optimization in e-Commercial Sponsored Search","created":"2021-06-08","cited_by_count":7,"area":null},{"id":"2204.04558","title":"Gradient-Based Trajectory Optimization With Learned Dynamics","created":"2022-04-09","cited_by_count":7,"area":null},{"id":"2310.17786","title":"Understanding when Dynamics-Invariant Data Augmentations Benefit Model-Free Reinforcement Learning Updates","created":"2023-10-26","cited_by_count":7,"area":null},{"id":"2110.01954","title":"Continuous-Time Fitted Value Iteration for Robust Policies","created":"2021-10-05","cited_by_count":6,"area":null},{"id":"2112.11216","title":"Value Activation for Bias Alleviation: Generalized-activated Deep Double Deterministic Policy Gradients","created":"2021-12-21","cited_by_count":6,"area":null},{"id":"2104.01036","title":"Hybrid Policy Learning for Energy-Latency Tradeoff in MEC-Assisted VR Video Service","created":"2021-04-02","cited_by_count":5,"area":null},{"id":"2209.13126","title":"Design of experiments for the calibration of history-dependent models via deep reinforcement learning and an enhanced Kalman filter","created":"2022-09-27","cited_by_count":5,"area":null},{"id":"2306.07552","title":"Galactic: Scaling End-to-End Reinforcement Learning for Rearrangement at 100k Steps-Per-Second","created":"2023-06-13","cited_by_count":5,"area":null},{"id":"2101.09933","title":"A Survey on Active Deep Learning: From Model-driven to Data-driven","created":"2021-01-25","cited_by_count":4,"area":null},{"id":"2104.04080","title":"Design and implementation of an environment for Learning to Run a Power Network (L2RPN)","created":"2021-04-06","cited_by_count":4,"area":null},{"id":"2410.03924","title":"Online Control-Informed Learning","created":"2024-10-04","cited_by_count":4,"area":null},{"id":"2111.12197","title":"Fixed Points in Cyber Space: Rethinking Optimal Evasion Attacks in the Age of AI-NIDS","created":"2021-11-23","cited_by_count":3,"area":null},{"id":"2208.12136","title":"A Comparison of Reinforcement Learning Frameworks for Software Testing Tasks","created":"2022-08-25","cited_by_count":3,"area":null},{"id":"2212.01343","title":"CT-DQN: Control-Tutored Deep Reinforcement Learning","created":"2022-12-02","cited_by_count":3,"area":null},{"id":"2402.18016","title":"User Decision Guidance with Selective Explanation Presentation from Explainable-AI","created":"2024-02-28","cited_by_count":3,"area":null},{"id":"2410.03915","title":"Distribution Guided Active Feature Acquisition","created":"2024-10-04","cited_by_count":3,"area":null},{"id":"2109.01768","title":"Eden: A Unified Environment Framework for Booming Reinforcement Learning Algorithms","created":"2021-09-04","cited_by_count":2,"area":null},{"id":"2205.12770","title":"An Experimental Comparison Between Temporal Difference and Residual Gradient with Neural Network Approximation","created":"2022-05-25","cited_by_count":2,"area":null},{"id":"2304.10590","title":"A Review of Symbolic, Subsymbolic and Hybrid Methods for Sequential Decision Making","created":"2023-04-20","cited_by_count":2,"area":null},{"id":"2310.13230","title":"Absolute Policy Optimization","created":"2023-10-20","cited_by_count":2,"area":null},{"id":"2411.14991","title":"Free Energy Projective Simulation (FEPS): Active inference with interpretability","created":"2024-11-22","cited_by_count":2,"area":null},{"id":"2103.14256","title":"Learning Reactive and Predictive Differentiable Controllers for Switching Linear Dynamical Models","created":"2021-03-26","cited_by_count":1,"area":null},{"id":"2104.10403","title":"Model-aided Deep Reinforcement Learning for Sample-efficient UAV Trajectory Design in IoT Networks","created":"2021-04-21","cited_by_count":1,"area":null},{"id":"2106.10533","title":"Learning to Reach, Swim, Walk and Fly in One Trial: Data-Driven Control with Scarce Data and Side Information","created":"2021-06-19","cited_by_count":1,"area":null},{"id":"2106.14080","title":"Model-Advantage and Value-Aware Models for Model-Based Reinforcement Learning: Bridging the Gap in Theory and Practice","created":"2021-06-26","cited_by_count":1,"area":null},{"id":"2111.08108","title":"Physics-informed neural networks via stochastic Hamiltonian dynamics learning","created":"2021-11-15","cited_by_count":1,"area":null},{"id":"2202.08444","title":"A Survey on Deep Reinforcement Learning-based Approaches for Adaptation and Generalization","created":"2022-02-17","cited_by_count":1,"area":null},{"id":"2207.00636","title":"Action-modulated midbrain dopamine activity arises from distributed control policies","created":"2022-07-01","cited_by_count":1,"area":null},{"id":"2207.11161","title":"Lagrangian Method for Q-Function Learning (with Applications to Machine Translation)","created":"2022-07-22","cited_by_count":1,"area":null},{"id":"2209.10458","title":"Model-Free Reinforcement Learning for Asset Allocation","created":"2022-09-21","cited_by_count":1,"area":null},{"id":"2210.12892","title":"AACHER: Assorted Actor-Critic Deep Reinforcement Learning with Hindsight Experience Replay","created":"2022-10-24","cited_by_count":1,"area":null},{"id":"2211.05338","title":"Job Scheduling in Datacenters using Constraint Controlled RL","created":"2022-11-10","cited_by_count":1,"area":null},{"id":"2212.08949","title":"Managing Temporal Resolution in Continuous Value Estimation: A Fundamental Trade-off","created":"2022-12-17","cited_by_count":1,"area":null},{"id":"2305.07448","title":"Deep Deterministic Policy Gradient for End-to-End Communication Systems without Prior Channel Knowledge","created":"2023-05-12","cited_by_count":1,"area":null},{"id":"2307.12083","title":"Active Control of Flow over Rotating Cylinder by Multiple Jets using Deep Reinforcement Learning","created":"2023-07-22","cited_by_count":1,"area":null},{"id":"2504.11258","title":"Multi-Agent Reinforcement Learning for Greenhouse Gas Offset Credit Markets","created":"2025-04-15","cited_by_count":1,"area":null},{"id":"2101.07175","title":"Deep Reinforcement Learning with Embedded LQR Controllers","created":"2021-01-18","cited_by_count":0,"area":null},{"id":"2102.08029","title":"Transferring Domain Knowledge with an Adviser in Continuous Tasks","created":"2021-02-16","cited_by_count":0,"area":null},{"id":"2103.14474","title":"Composable Learning with Sparse Kernel Representations","created":"2021-03-26","cited_by_count":0,"area":null},{"id":"2104.01980","title":"Probabilistic Programming Bots in Intuitive Physics Game Play","created":"2021-04-05","cited_by_count":0,"area":null},{"id":"2104.08543","title":"Planning with Expectation Models for Control","created":"2021-04-17","cited_by_count":0,"area":null},{"id":"2107.08378","title":"Co-designing Intelligent Control of Building HVACs and Microgrids","created":"2021-07-18","cited_by_count":0,"area":null},{"id":"2109.13463","title":"Deep Reinforcement Learning with Adjustments","created":"2021-09-28","cited_by_count":0,"area":null},{"id":"2201.11783","title":"Boosting Exploration in Multi-Task Reinforcement Learning using Adversarial Networks","created":"2022-01-27","cited_by_count":0,"area":null},{"id":"2202.13436","title":"Neural-Progressive Hedging: Enforcing Constraints in Reinforcement Learning with Stochastic Programming","created":"2022-02-27","cited_by_count":0,"area":null},{"id":"2206.14802","title":"Visual Foresight With a Local Dynamics Model","created":"2022-06-29","cited_by_count":0,"area":null},{"id":"2210.13545","title":"MEET: A Monte Carlo Exploration-Exploitation Trade-off for Buffer Sampling","created":"2022-10-24","cited_by_count":0,"area":null},{"id":"2211.04001","title":"Progress and summary of reinforcement learning on energy management of MPS-EV","created":"2022-11-08","cited_by_count":0,"area":null},{"id":"2302.14182","title":"Taylor TD-learning","created":"2023-02-27","cited_by_count":0,"area":null},{"id":"2307.08168","title":"Enabling Efficient, Reliable Real-World Reinforcement Learning with Approximate Physics-Based Models","created":"2023-07-16","cited_by_count":0,"area":null},{"id":"2312.02649","title":"A Q-learning approach to the continuous control problem of robot inverted pendulum balancing","created":"2023-12-05","cited_by_count":0,"area":null},{"id":"2312.17284","title":"Dynamic Decision Making in Engineering System Design: A Deep Q-Learning Approach","created":"2023-12-28","cited_by_count":0,"area":null},{"id":"2403.05732","title":"Conservative DDPG -- Pessimistic RL without Ensemble","created":"2024-03-08","cited_by_count":0,"area":null},{"id":"2403.14550","title":"Dynamic Explanation Emphasis in Human-XAI Interaction with Communication Robot","created":"2024-03-21","cited_by_count":0,"area":null},{"id":"2405.00902","title":"MESA: Cooperative Meta-Exploration in Multi-Agent Learning through Exploiting State-Action Space Structure","created":"2024-05-01","cited_by_count":0,"area":null},{"id":"2602.12520","title":"Multi-Agent Model-Based Reinforcement Learning with Joint State-Action Learned Embeddings","created":"2026-02-13","cited_by_count":0,"area":null},{"id":"2604.06180","title":"MedRoute: RL-Based Dynamic Specialist Routing in Multi-Agent Medical Diagnosis","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2609.04698","title":"LookThere! Sparse Vision by Reinforced Selection","created":"2026-09-04","cited_by_count":0,"area":null}],"next_cursor":null}