{"list":"other","total":61,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807},{"id":"1710.02298","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","created":"2017-10-06","cited_by_count":786},{"id":"1511.06581","title":"Dueling Network Architectures for Deep Reinforcement Learning","created":"2015-11-20","cited_by_count":785},{"id":"2004.04136","title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","created":"2020-04-08","cited_by_count":760},{"id":"2002.00444","title":"Deep Reinforcement Learning for Autonomous Driving: A Survey","created":"2020-02-02","cited_by_count":721},{"id":"1608.04636","title":"Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-\\L{}ojasiewicz Condition","created":"2016-08-16","cited_by_count":539},{"id":"1602.04621","title":"Deep Exploration via Bootstrapped DQN","created":"2016-02-15","cited_by_count":527},{"id":"2006.10742","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","created":"2020-06-18","cited_by_count":436},{"id":"1611.05397","title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","created":"2016-11-16","cited_by_count":404},{"id":"2107.09645","title":"Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning","created":"2021-07-20","cited_by_count":372},{"id":"2306.13831","title":"Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks","created":"2023-06-24","cited_by_count":327},{"id":"2007.05929","title":"Data-Efficient Reinforcement Learning with Self-Predictive Representations","created":"2020-07-12","cited_by_count":318},{"id":"1606.01541","title":"Deep Reinforcement Learning for Dialogue Generation","created":"2016-06-05","cited_by_count":288},{"id":"1604.06057","title":"Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation","created":"2016-04-20","cited_by_count":286},{"id":"1709.06009","title":"Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents","created":"2017-09-18","cited_by_count":269},{"id":"2009.08319","title":"Decoupling Representation Learning from Reinforcement Learning","created":"2020-09-14","cited_by_count":269},{"id":"1812.02690","title":"Provably Efficient Maximum Entropy Exploration","created":"2018-12-06","cited_by_count":242},{"id":"1802.02246","title":"Approximation Methods for Bilevel Programming","created":"2018-02-06","cited_by_count":236},{"id":"1611.03673","title":"Learning to Navigate in Complex Environments","created":"2016-11-11","cited_by_count":198},{"id":"1812.02648","title":"Deep Reinforcement Learning and the Deadly Triad","created":"2018-12-06","cited_by_count":174},{"id":"2001.03040","title":"Deep Network Approximation for Smooth Functions","created":"2020-01-09","cited_by_count":164},{"id":"1906.08226","title":"Unsupervised State Representation Learning in Atari","created":"2019-06-19","cited_by_count":144},{"id":"2007.05170","title":"A Two-Timescale Framework for Bilevel Optimization: Complexity Analysis and Application to Actor-Critic","created":"2020-07-10","cited_by_count":144},{"id":"1711.00138","title":"Visualizing and Understanding Atari Agents","created":"2017-10-31","cited_by_count":141},{"id":"2010.14498","title":"Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement Learning","created":"2020-10-27","cited_by_count":134},{"id":"1908.03568","title":"Behaviour Suite for Reinforcement Learning","created":"2019-08-09","cited_by_count":132},{"id":"1802.04181","title":"State Representation Learning for Control: An Overview","created":"2018-02-12","cited_by_count":127},{"id":"2204.09560","title":"Understanding and Preventing Capacity Loss in Reinforcement Learning","created":"2022-04-20","cited_by_count":125},{"id":"2101.05265","title":"Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning","created":"2021-01-13","cited_by_count":123},{"id":"2209.08709","title":"BOME! Bilevel Optimization Made Easy: A Simple First-Order Approach","created":"2022-09-19","cited_by_count":105},{"id":"2210.05639","title":"Discovered Policy Optimisation","created":"2022-10-11","cited_by_count":104},{"id":"2301.10945","title":"A Fully First-Order Method for Stochastic Bilevel Optimization","created":"2023-01-26","cited_by_count":100},{"id":"2306.02451","title":"For SALE: State-Action Representation Learning for Deep Reinforcement Learning","created":"2023-06-04","cited_by_count":75},{"id":"2010.08843","title":"Approximate information state for approximate planning and reinforcement learning in partially observed systems","created":"2020-10-17","cited_by_count":70},{"id":"2006.02243","title":"The Value-Improvement Path: Towards Better Representations for Reinforcement Learning","created":"2020-06-03","cited_by_count":60},{"id":"2007.12401","title":"Predictive Information Accelerates Learning in RL","created":"2020-07-24","cited_by_count":56},{"id":"1901.11530","title":"A Geometric Perspective on Optimal Representations for Reinforcement Learning","created":"2019-01-31","cited_by_count":54},{"id":"2210.02019","title":"Atari-5: Distilling the Arcade Learning Environment down to Five Games","created":"2022-10-05","cited_by_count":44},{"id":"2308.00788","title":"An Introduction to Bi-level Optimization: Foundations and Applications in Signal Processing and Machine Learning","created":"2023-08-01","cited_by_count":41},{"id":"2102.10960","title":"Return-Based Contrastive Representation Learning for Reinforcement Learning","created":"2021-02-22","cited_by_count":36},{"id":"2206.09527","title":"Simultaneous approximation of a smooth function and its derivatives by deep neural networks with piecewise-polynomial activations","created":"2022-06-20","cited_by_count":29},{"id":"2108.09003","title":"Explainable Reinforcement Learning for Broad-XAI: A Conceptual Framework and Survey","created":"2021-08-20","cited_by_count":24},{"id":"2203.15955","title":"Investigating the Properties of Neural Network Representations in Reinforcement Learning","created":"2022-03-30","cited_by_count":24},{"id":"2107.05431","title":"CoBERL: Contrastive BERT for Reinforcement Learning","created":"2021-07-12","cited_by_count":21},{"id":"2403.20233","title":"Functional Bilevel Optimization for Machine Learning","created":"2024-03-29","cited_by_count":20},{"id":"2312.11669","title":"Prediction and Control in Continual Reinforcement Learning","created":"2023-12-18","cited_by_count":19},{"id":"1705.10422","title":"Learning End-to-end Multimodal Sensor Policies for Autonomous Navigation","created":"2017-05-30","cited_by_count":18},{"id":"1908.08578","title":"On Convergence Rate of Adaptive Multiscale Value Function Approximation For Reinforcement Learning","created":"2019-08-22","cited_by_count":12},{"id":"2210.03209","title":"Self-Adaptive Driving in Nonstationary Environments through Conjectural Online Lookahead Adaptation","created":"2022-10-06","cited_by_count":12},{"id":"2306.06766","title":"Digital Twin-Enhanced Wireless Indoor Navigation: Achieving Efficient Environment Sensing with Zero-Shot Reinforcement Learning","created":"2023-06-11","cited_by_count":11},{"id":"2410.17431","title":"Meta Stackelberg Game: Robust Federated Learning against Adaptive and Mixed Poisoning Attacks","created":"2024-10-22","cited_by_count":9},{"id":"2503.06343","title":"Studying the Interplay Between the Actor and Critic Representations in Reinforcement Learning","created":"2025-03-08","cited_by_count":8},{"id":"2208.00081","title":"Sampling Attacks on Meta Reinforcement Learning: A Minimax Formulation and Complexity Analysis","created":"2022-07-29","cited_by_count":5},{"id":"2503.00385","title":"Model-Agnostic Meta-Policy Optimization via Zeroth-Order Estimation: A Linear Quadratic Regulator Perspective","created":"2025-03-01","cited_by_count":3}],"next_cursor":null}