{"total":102,"rows":[{"id":"2201.03916","title":"Automated Reinforcement Learning (AutoRL): A Survey and Open Problems","created":"2022-01-11","cited_by_count":70,"area":null},{"id":"2109.06668","title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain","created":"2021-09-14","cited_by_count":58,"area":null},{"id":"2107.05544","title":"Meta-learning PINN loss functions","created":"2021-07-12","cited_by_count":51,"area":null},{"id":"2109.04504","title":"Bootstrapped Meta-Learning","created":"2021-09-09","cited_by_count":45,"area":null},{"id":"2105.13345","title":"Adversarial Intrinsic Motivation for Reinforcement Learning","created":"2021-05-27","cited_by_count":40,"area":"offlinerl"},{"id":"2408.10215","title":"Comprehensive Overview of Reward Engineering and Shaping in Advancing Reinforcement Learning Applications","created":"2024-07-22","cited_by_count":38,"area":"deeprl"},{"id":"2111.13485","title":"Learning Long-Term Reward Redistribution via Randomized Return Decomposition","created":"2021-11-26","cited_by_count":33,"area":null},{"id":"1912.07773","title":"MEDIRL: Predicting the Visual Attention of Drivers via Maximum Entropy Deep Inverse Reinforcement Learning","created":"2019-12-17","cited_by_count":29,"area":"offlinerl"},{"id":"2101.08152","title":"Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated Environments","created":"2021-01-20","cited_by_count":28,"area":null},{"id":"2106.10517","title":"A Max-Min Entropy Framework for Reinforcement Learning","created":"2021-06-19","cited_by_count":28,"area":null},{"id":"2102.06741","title":"Discovery of Options via Meta-Learned Subgoals","created":"2021-02-12","cited_by_count":27,"area":null},{"id":"1812.00950","title":"Generative Adversarial Self-Imitation Learning","created":"2018-12-03","cited_by_count":25,"area":"offlinerl"},{"id":"2106.11854","title":"Off-Policy Reinforcement Learning with Delayed Rewards","created":"2021-06-22","cited_by_count":25,"area":null},{"id":"2211.07627","title":"Redeeming Intrinsic Rewards via Constrained Optimization","created":"2022-11-14","cited_by_count":24,"area":null},{"id":"2204.02246","title":"Continuously Discovering Novel Strategies via Reward-Switching Policy Optimization","created":"2022-04-04","cited_by_count":23,"area":null},{"id":"2310.00697","title":"Learning How to Propagate Messages in Graph Neural Networks","created":"2023-10-01","cited_by_count":23,"area":null},{"id":"2506.15544","title":"Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning","created":"2025-06-18","cited_by_count":23,"area":"deeprl"},{"id":"2401.07382","title":"Beyond Sparse Rewards: Enhancing Reinforcement Learning with Language Model Critique in Text Generation","created":"2024-01-14","cited_by_count":22,"area":"alignment"},{"id":"2408.03029","title":"Highly Efficient Self-Adaptive Reward Shaping for Reinforcement Learning","created":"2024-08-06","cited_by_count":22,"area":"deeprl"},{"id":"2106.00669","title":"Discovering Diverse Nearly Optimal Policies with Successor Features","created":"2021-06-01","cited_by_count":20,"area":null},{"id":"2211.15457","title":"Hypernetworks for Zero-shot Transfer in Reinforcement Learning","created":"2022-11-28","cited_by_count":19,"area":null},{"id":"2301.10339","title":"AutoCost: Evolving Intrinsic Cost for Zero-violation Reinforcement Learning","created":"2023-01-24","cited_by_count":17,"area":null},{"id":"2310.19007","title":"Behavior Alignment via Reward Function Optimization","created":"2023-10-29","cited_by_count":16,"area":null},{"id":"2403.06826","title":"In-context Exploration-Exploitation for Reinforcement Learning","created":"2024-03-11","cited_by_count":16,"area":"offlinerl"},{"id":"2505.20417","title":"SCAR: Shapley Credit Assignment for More Efficient RLHF","created":"2025-05-26","cited_by_count":16,"area":"alignment"},{"id":"2302.01667","title":"Mind the Gap: Offline Policy Optimization for Imperfect Rewards","created":"2023-02-03","cited_by_count":15,"area":"offlinerl"},{"id":"2310.06794","title":"$f$-Policy Gradients: A General Framework for Goal Conditioned RL using $f$-Divergences","created":"2023-10-10","cited_by_count":14,"area":null},{"id":"2206.06426","title":"Provably Efficient Offline Reinforcement Learning with Trajectory-Wise Reward","created":"2022-06-13","cited_by_count":13,"area":"offlinerl"},{"id":"2506.01538","title":"LAMARL: LLM-Aided Multi-Agent Reinforcement Learning for Cooperative Policy Generation","created":"2025-06-02","cited_by_count":13,"area":"agents"},{"id":"2112.15400","title":"A Theoretical Understanding of Gradient Bias in Meta-Reinforcement Learning","created":"2021-12-31","cited_by_count":12,"area":null},{"id":"2301.10886","title":"Automatic Intrinsic Reward Shaping for Exploration in Deep Reinforcement Learning","created":"2023-01-26","cited_by_count":12,"area":null},{"id":"2209.06159","title":"Meta-Gradients in Non-Stationary Environments","created":"2022-09-13","cited_by_count":11,"area":null},{"id":"2210.05409","title":"LECO: Learnable Episodic Count for Task-Specific Intrinsic Reward","created":"2022-10-11","cited_by_count":11,"area":null},{"id":"2405.19697","title":"Bilevel reinforcement learning via the development of hyper-gradient without lower-level convexity","created":"2024-05-30","cited_by_count":10,"area":"deeprl"},{"id":"2103.09159","title":"Learning to Shape Rewards using a Game of Two Partners","created":"2021-03-16","cited_by_count":9,"area":null},{"id":"2311.03485","title":"CLIP-Motion: Learning Reward Functions for Robotic Actions Using Consecutive Observations","created":"2023-11-06","cited_by_count":9,"area":null},{"id":"2108.07783","title":"Toward a `Standard Model' of Machine Learning","created":"2021-08-17","cited_by_count":8,"area":null},{"id":"2111.15382","title":"Continuous Control With Ensemble Deep Deterministic Policy Gradients","created":"2021-11-30","cited_by_count":8,"area":null},{"id":"2201.04286","title":"Evolutionary Action Selection for Gradient-based Policy Learning","created":"2022-01-12","cited_by_count":7,"area":null},{"id":"2407.16186","title":"Automatic Environment Shaping is the Next Frontier in RL","created":"2024-07-23","cited_by_count":7,"area":null},{"id":"2110.15331","title":"Wasserstein Distance Maximizing Intrinsic Control","created":"2021-10-28","cited_by_count":6,"area":null},{"id":"2202.02790","title":"Learning Synthetic Environments and Reward Networks for Reinforcement Learning","created":"2022-02-06","cited_by_count":6,"area":null},{"id":"2307.15944","title":"PIMbot: Policy and Incentive Manipulation for Multi-Robot Reinforcement Learning in Social Dilemmas","created":"2023-07-29","cited_by_count":6,"area":null},{"id":"2508.08982","title":"Unsupervised Skill Discovery as Exploration for Learning Agile Locomotion","created":"2025-08-12","cited_by_count":6,"area":null},{"id":"2103.14600","title":"Model-Free Learning of Safe yet Effective Controllers","created":"2021-03-26","cited_by_count":5,"area":null},{"id":"2106.04499","title":"Towards Practical Credit Assignment for Deep Reinforcement Learning","created":"2021-06-08","cited_by_count":5,"area":null},{"id":"2111.00206","title":"One Step at a Time: Pros and Cons of Multi-Step Meta-Gradient Reinforcement Learning","created":"2021-10-30","cited_by_count":5,"area":null},{"id":"2202.08266","title":"Open-Ended Reinforcement Learning with Neural Reward Functions","created":"2022-02-16","cited_by_count":5,"area":null},{"id":"2209.11303","title":"An Investigation of the Bias-Variance Tradeoff in Meta-Gradients","created":"2022-09-22","cited_by_count":5,"area":null},{"id":"2406.18293","title":"Combining Automated Optimisation of Hyperparameters and Reward Shape","created":"2024-06-26","cited_by_count":5,"area":"deeprl"},{"id":"2106.05402","title":"Deception in Social Learning: A Multi-Agent Reinforcement Learning Perspective","created":"2021-06-09","cited_by_count":4,"area":null},{"id":"2202.12174","title":"Collaborative Training of Heterogeneous Reinforcement Learning Agents in Environments with Sparse Rewards: What and When to Share?","created":"2022-02-24","cited_by_count":4,"area":null},{"id":"2210.00293","title":"Deep Intrinsically Motivated Exploration in Continuous Control","created":"2022-10-01","cited_by_count":4,"area":null},{"id":"2409.05358","title":"BAMDP Shaping: a Unified Framework for Intrinsic Motivation and Reward Shaping","created":"2024-09-09","cited_by_count":4,"area":"deeprl"},{"id":"2101.09721","title":"Learning Synthetic Environments for Reinforcement Learning with Evolution Strategies","created":"2021-01-24","cited_by_count":3,"area":null},{"id":"2210.16956","title":"Reward Shaping Using Convolutional Neural Network","created":"2022-10-30","cited_by_count":3,"area":null},{"id":"2307.04962","title":"Intrinsically motivated graph exploration using network theories of human curiosity","created":"2023-07-11","cited_by_count":3,"area":null},{"id":"2402.07019","title":"Informativeness of Reward Functions in Reinforcement Learning","created":"2024-02-10","cited_by_count":3,"area":"deeprl"},{"id":"2510.17697","title":"A Principle of Targeted Intervention for Multi-Agent Reinforcement Learning","created":"2025-10-20","cited_by_count":3,"area":null},{"id":"2102.04999","title":"Adaptive Pairwise Weights for Temporal Credit Assignment","created":"2021-02-09","cited_by_count":2,"area":null},{"id":"2102.12957","title":"Credit Assignment with Meta-Policy Gradient for Multi-Agent Reinforcement Learning","created":"2021-02-24","cited_by_count":2,"area":null},{"id":"2104.04174","title":"Learning to Reweight Imaginary Transitions for Model-Based Reinforcement Learning","created":"2021-04-09","cited_by_count":2,"area":null},{"id":"2106.02745","title":"Neural Auto-Curricula","created":"2021-06-04","cited_by_count":2,"area":null},{"id":"2206.01011","title":"Policy Gradient Algorithms with Monte Carlo Tree Learning for Non-Markov Decision Processes","created":"2022-06-02","cited_by_count":2,"area":null},{"id":"2410.20176","title":"Beyond Simple Sum of Delayed Rewards: Non-Markovian Reward Modeling for Reinforcement Learning","created":"2024-10-26","cited_by_count":2,"area":"alignment"},{"id":"2505.20671","title":"LLM-Guided Reinforcement Learning: Addressing Training Bottlenecks through Policy Modulation","created":"2025-05-27","cited_by_count":2,"area":null},{"id":"2508.21443","title":"Beyond expected value: geometric mean optimization for long-term policy performance in reinforcement learning","created":"2025-08-29","cited_by_count":2,"area":"deeprl"},{"id":"2510.12334","title":"Finite-time Convergence Analysis of Actor-Critic with Evolving Reward","created":"2025-10-14","cited_by_count":2,"area":"deeprl"},{"id":"2511.05849","title":"EGG-SR: Embedding Symbolic Equivalence into Symbolic Regression via Equality Graph","created":"2025-11-08","cited_by_count":2,"area":null},{"id":"2303.09027","title":"Learning Rewards to Optimize Global Performance Metrics in Deep Reinforcement Learning","created":"2023-03-16","cited_by_count":1,"area":null},{"id":"2403.11330","title":"Improving Dialogue Agents by Decomposing One Global Explicit Annotation with Local Implicit Multimodal Feedback","created":"2024-03-17","cited_by_count":1,"area":"agents"},{"id":"2404.07826","title":"On the Sample Efficiency of Abstractions and Potential-Based Reward Shaping in Reinforcement Learning","created":"2024-04-11","cited_by_count":1,"area":"deeprl"},{"id":"2407.21546","title":"Black Box Meta-Learning Intrinsic Rewards","created":"2024-07-31","cited_by_count":1,"area":"deeprl"},{"id":"2412.17123","title":"Fairness in Reinforcement Learning with Bisimulation Metrics","created":"2024-12-22","cited_by_count":1,"area":"deeprl"},{"id":"2505.07911","title":"Combining Bayesian Inference and Reinforcement Learning for Agent Decision Making: A Review","created":"2025-05-12","cited_by_count":1,"area":"deeprl"},{"id":"2512.04723","title":"CIG-MAE: Cross-Modal Information-Guided Masked Autoencoder for Self-Supervised WiFi Sensing","created":"2025-12-04","cited_by_count":1,"area":null},{"id":"2512.13837","title":"Explainable reinforcement learning from human feedback to improve alignment","created":"2025-12-15","cited_by_count":1,"area":"alignment"},{"id":"2601.11890","title":"From Relative Entropy to Minimax: A Unified Framework for Coverage in MDPs","created":"2026-01-17","cited_by_count":1,"area":null},{"id":"2604.28056","title":"RHyVE: Competence-Aware Verification and Phase-Aware Deployment for LLM-Generated Reward Hypotheses","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2605.23027","title":"PIMbot: A Self-Adaptive Attack Framework for Adversarial Manipulation of Multi-Robot Reinforcement Learning","created":"2026-05-21","cited_by_count":1,"area":"deeprl"},{"id":"2102.10527","title":"Delayed Rewards Calibration via Reward Empirical Sufficiency","created":"2021-02-21","cited_by_count":0,"area":null},{"id":"2207.14722","title":"Automatic Reward Design via Learning Motivation-Consistent Intrinsic Rewards","created":"2022-07-29","cited_by_count":0,"area":null},{"id":"2211.10550","title":"Debiasing Meta-Gradient Reinforcement Learning by Learning the Outer Value Function","created":"2022-11-19","cited_by_count":0,"area":null},{"id":"2211.10660","title":"Evaluating the Perceived Safety of Urban City via Maximum Entropy Deep Inverse Reinforcement Learning","created":"2022-11-19","cited_by_count":0,"area":"offlinerl"},{"id":"2211.11649","title":"Implicit Training of Energy Model for Structure Prediction","created":"2022-11-21","cited_by_count":0,"area":null},{"id":"2212.11726","title":"Reusable Options through Gradient-based Meta Learning","created":"2022-12-22","cited_by_count":0,"area":null},{"id":"2306.10587","title":"Acceleration in Policy Optimization","created":"2023-06-18","cited_by_count":0,"area":null},{"id":"2308.00629","title":"Dependency Structure Search Bayesian Optimization for Decision Making Models","created":"2023-08-01","cited_by_count":0,"area":null},{"id":"2312.03216","title":"SDSRA: A Skill-Driven Skill-Recombination Algorithm for Efficient Policy Learning","created":"2023-12-06","cited_by_count":0,"area":null},{"id":"2312.05783","title":"DCIR: Dynamic Consistency Intrinsic Reward for Multi-Agent Reinforcement Learning","created":"2023-12-10","cited_by_count":0,"area":null},{"id":"2402.03771","title":"Reinforcement Learning from Bagged Reward","created":"2024-02-06","cited_by_count":0,"area":"deeprl"},{"id":"2407.05580","title":"$\\mathrm{E^{2}CFD}$: Towards Effective and Efficient Cost Function Design for Safe Reinforcement Learning via Large Language Model","created":"2024-07-08","cited_by_count":0,"area":null},{"id":"2501.07346","title":"Enhancing Online Reinforcement Learning with Meta-Learned Objective from Offline Data","created":"2025-01-13","cited_by_count":0,"area":"offlinerl"},{"id":"2507.11875","title":"DualReward: A Dynamic Reinforcement Learning Framework for Cloze Tests Distractor Generation","created":"2025-07-16","cited_by_count":0,"area":"deeprl"},{"id":"2512.15948","title":"Subjective functions","created":"2025-12-17","cited_by_count":0,"area":null},{"id":"2601.08107","title":"STO-RL: Offline RL under Sparse Rewards via LLM-Guided Subgoal Temporal Order","created":"2026-01-13","cited_by_count":0,"area":"offlinerl"},{"id":"2602.20404","title":"$\\kappa$-Explorer: A Unified Framework for Active Model Estimation in MDPs","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2605.02073","title":"Enhanced LLM Reasoning by Optimizing Reward Functions with Search-Driven Reinforcement Learning","created":"2026-05-03","cited_by_count":0,"area":"lr"},{"id":"2606.05586","title":"BMCR: Adaptive Backbone Module Composition via Reinforcement Learning for Remote Sensing Object Detection","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.10129","title":"Discovering Interpretable Multi-Parameter Control Policies for Evolutionary Algorithms Using Deep Reinforcement Learning","created":"2026-06-08","cited_by_count":0,"area":"deeprl"}],"next_cursor":"100"}