{"total":107,"rows":[{"id":"2104.02008","title":"Domain Generalization with MixStyle","created":"2021-04-05","cited_by_count":566,"area":null},{"id":"2205.07802","title":"The Primacy Bias in Deep Reinforcement Learning","created":"2022-05-16","cited_by_count":247,"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":"2203.01302","title":"Evolving Curricula with Regret-Based Environment Design","created":"2022-03-02","cited_by_count":173,"area":null},{"id":"2111.09794","title":"A Survey of Zero-shot Generalisation in Deep Reinforcement Learning","created":"2021-11-18","cited_by_count":170,"area":null},{"id":"2101.05265","title":"Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning","created":"2021-01-13","cited_by_count":123,"area":null},{"id":"2110.05038","title":"Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs","created":"2021-10-11","cited_by_count":122,"area":null},{"id":"2107.06277","title":"Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability","created":"2021-07-13","cited_by_count":109,"area":null},{"id":"2106.04799","title":"Pretraining Representations for Data-Efficient Reinforcement Learning","created":"2021-06-09","cited_by_count":105,"area":null},{"id":"2107.00644","title":"Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation","created":"2021-07-01","cited_by_count":105,"area":null},{"id":"2102.10330","title":"Decoupling Value and Policy for Generalization in Reinforcement Learning","created":"2021-02-20","cited_by_count":82,"area":null},{"id":"2112.13112","title":"A Survey on Interpretable Reinforcement Learning","created":"2021-12-24","cited_by_count":73,"area":null},{"id":"2201.03916","title":"Automated Reinforcement Learning (AutoRL): A Survey and Open Problems","created":"2022-01-11","cited_by_count":70,"area":null},{"id":"2107.02053","title":"MixStyle Neural Networks for Domain Generalization and Adaptation","created":"2021-07-05","cited_by_count":64,"area":null},{"id":"2210.05805","title":"Exploration via Elliptical Episodic Bonuses","created":"2022-10-11","cited_by_count":51,"area":null},{"id":"2102.04376","title":"Adversarially Guided Actor-Critic","created":"2021-02-08","cited_by_count":47,"area":null},{"id":"2110.10067","title":"CORA: Benchmarks, Baselines, and Metrics as a Platform for Continual Reinforcement Learning Agents","created":"2021-10-19","cited_by_count":38,"area":null},{"id":"2209.09203","title":"Look where you look! Saliency-guided Q-networks for generalization in visual Reinforcement Learning","created":"2022-09-16","cited_by_count":34,"area":null},{"id":"2102.13268","title":"DRIBO: Robust Deep Reinforcement Learning via Multi-View Information Bottleneck","created":"2021-02-26","cited_by_count":31,"area":null},{"id":"2306.05483","title":"On the Importance of Exploration for Generalization in Reinforcement Learning","created":"2023-06-08","cited_by_count":31,"area":null},{"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":"2307.01452","title":"Causal Reinforcement Learning: A Survey","created":"2023-07-04","cited_by_count":23,"area":null},{"id":"2102.08370","title":"Quantifying the effects of environment and population diversity in multi-agent reinforcement learning","created":"2021-02-16","cited_by_count":22,"area":null},{"id":"2202.09982","title":"Don't Touch What Matters: Task-Aware Lipschitz Data Augmentation for Visual Reinforcement Learning","created":"2022-02-21","cited_by_count":21,"area":null},{"id":"2301.12950","title":"Hierarchical Programmatic Reinforcement Learning via Learning to Compose Programs","created":"2023-01-30","cited_by_count":20,"area":null},{"id":"2306.03236","title":"A Study of Global and Episodic Bonuses for Exploration in Contextual MDPs","created":"2023-06-05","cited_by_count":20,"area":null},{"id":"2102.07097","title":"Domain Adversarial Reinforcement Learning","created":"2021-02-14","cited_by_count":19,"area":null},{"id":"2106.01151","title":"Towards Deeper Deep Reinforcement Learning with Spectral Normalization","created":"2021-06-02","cited_by_count":19,"area":null},{"id":"2205.06760","title":"Emergent Bartering Behaviour in Multi-Agent Reinforcement Learning","created":"2022-05-13","cited_by_count":19,"area":null},{"id":"2207.05480","title":"Temporal Disentanglement of Representations for Improved Generalisation in Reinforcement Learning","created":"2022-07-12","cited_by_count":19,"area":null},{"id":"2103.09815","title":"TeachMyAgent: a Benchmark for Automatic Curriculum Learning in Deep RL","created":"2021-03-17","cited_by_count":18,"area":null},{"id":"2210.13417","title":"Avalon: A Benchmark for RL Generalization Using Procedurally Generated Worlds","created":"2022-10-24","cited_by_count":17,"area":null},{"id":"2106.15587","title":"Generalization of Reinforcement Learning with Policy-Aware Adversarial Data Augmentation","created":"2021-06-29","cited_by_count":15,"area":null},{"id":"2401.00678","title":"General-purpose foundation models for increased autonomy in robot-assisted surgery","created":"2024-01-01","cited_by_count":15,"area":null},{"id":"2206.02126","title":"Learning Dynamics and Generalization in Reinforcement Learning","created":"2022-06-05","cited_by_count":14,"area":null},{"id":"2310.11428","title":"Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression","created":"2023-10-17","cited_by_count":14,"area":null},{"id":"2203.08222","title":"Zipfian environments for Reinforcement Learning","created":"2022-03-15","cited_by_count":13,"area":null},{"id":"2306.00656","title":"Normalization Enhances Generalization in Visual Reinforcement Learning","created":"2023-06-01","cited_by_count":13,"area":null},{"id":"2105.13524","title":"Improving Generalization in Meta-RL with Imaginary Tasks from Latent Dynamics Mixture","created":"2021-05-28","cited_by_count":12,"area":null},{"id":"2107.05686","title":"The Role of Pretrained Representations for the OOD Generalization of Reinforcement Learning Agents","created":"2021-07-12","cited_by_count":12,"area":null},{"id":"2104.09368","title":"Deep Reinforcement Learning in a Monetary Model","created":"2021-04-19","cited_by_count":11,"area":null},{"id":"2209.08660","title":"Learn the Time to Learn: Replay Scheduling in Continual Learning","created":"2022-09-18","cited_by_count":11,"area":null},{"id":"2501.13075","title":"Evolution and The Knightian Blindspot of Machine Learning","created":"2025-01-22","cited_by_count":11,"area":null},{"id":"2306.02419","title":"Bad Habits: Policy Confounding and Out-of-Trajectory Generalization in RL","created":"2023-06-04","cited_by_count":10,"area":null},{"id":"2311.01642","title":"Robust Adversarial Reinforcement Learning via Bounded Rationality Curricula","created":"2023-11-03","cited_by_count":10,"area":null},{"id":"2312.15339","title":"MaDi: Learning to Mask Distractions for Generalization in Visual Deep Reinforcement Learning","created":"2023-12-23","cited_by_count":10,"area":null},{"id":"2203.00715","title":"Learning Robust Real-Time Cultural Transmission without Human Data","created":"2022-03-01","cited_by_count":9,"area":null},{"id":"2204.06355","title":"Local Feature Swapping for Generalization in Reinforcement Learning","created":"2022-04-13","cited_by_count":9,"area":null},{"id":"2307.11546","title":"Towards practical reinforcement learning for tokamak magnetic control","created":"2023-07-21","cited_by_count":9,"area":null},{"id":"2310.04128","title":"Reinforcement Learning with Fast and Forgetful Memory","created":"2023-10-06","cited_by_count":9,"area":null},{"id":"2210.00498","title":"EUCLID: Towards Efficient Unsupervised Reinforcement Learning with Multi-choice Dynamics Model","created":"2022-10-02","cited_by_count":8,"area":null},{"id":"2210.09960","title":"Rethinking Value Function Learning for Generalization in Reinforcement Learning","created":"2022-10-18","cited_by_count":8,"area":null},{"id":"2210.12871","title":"Tighter Abstract Queries in Neural Network Verification","created":"2022-10-23","cited_by_count":8,"area":null},{"id":"2410.12164","title":"Table-LLM-Specialist: Language Model Specialists for Tables using Iterative Generator-Validator Fine-tuning","created":"2024-10-16","cited_by_count":8,"area":null},{"id":"2111.12064","title":"Semantic-Aware Collaborative Deep Reinforcement Learning Over Wireless Cellular Networks","created":"2021-11-23","cited_by_count":6,"area":null},{"id":"2203.07454","title":"L2Explorer: A Lifelong Reinforcement Learning Assessment Environment","created":"2022-03-14","cited_by_count":6,"area":null},{"id":"2211.13337","title":"Multi-Environment Pretraining Enables Transfer to Action Limited Datasets","created":"2022-11-23","cited_by_count":5,"area":null},{"id":"2303.01668","title":"RePreM: Representation Pre-training with Masked Model for Reinforcement Learning","created":"2023-03-03","cited_by_count":5,"area":null},{"id":"2305.04832","title":"Sim2Rec: A Simulator-based Decision-making Approach to Optimize Real-World Long-term User Engagement in Sequential Recommender Systems","created":"2023-05-03","cited_by_count":5,"area":null},{"id":"2307.11685","title":"Towards Generalizable Reinforcement Learning for Trade Execution","created":"2023-05-12","cited_by_count":5,"area":null},{"id":"2207.06105","title":"GriddlyJS: A Web IDE for Reinforcement Learning","created":"2022-07-13","cited_by_count":4,"area":null},{"id":"2207.07749","title":"Bootstrap State Representation using Style Transfer for Better Generalization in Deep Reinforcement Learning","created":"2022-07-15","cited_by_count":4,"area":null},{"id":"2303.17655","title":"Q-Learning based system for path planning with unmanned aerial vehicles swarms in obstacle environments","created":"2023-03-30","cited_by_count":4,"area":null},{"id":"2312.10289","title":"Active Reinforcement Learning for Robust Building Control","created":"2023-12-16","cited_by_count":4,"area":null},{"id":"2102.11893","title":"Honey, I Shrunk The Actor: A Case Study on Preserving Performance with Smaller Actors in Actor-Critic RL","created":"2021-02-23","cited_by_count":3,"area":null},{"id":"2104.06153","title":"The Impact of Activation Sparsity on Overfitting in Convolutional Neural Networks","created":"2021-04-13","cited_by_count":3,"area":null},{"id":"2102.04220","title":"Grid-to-Graph: Flexible Spatial Relational Inductive Biases for Reinforcement Learning","created":"2021-02-08","cited_by_count":2,"area":null},{"id":"2207.02134","title":"Balancing Profit, Risk, and Sustainability for Portfolio Management","created":"2022-06-06","cited_by_count":2,"area":null},{"id":"2208.14863","title":"Style-Agnostic Reinforcement Learning","created":"2022-08-31","cited_by_count":2,"area":null},{"id":"2210.05393","title":"Exploration Policies for On-the-Fly Controller Synthesis: A Reinforcement Learning Approach","created":"2022-10-07","cited_by_count":2,"area":null},{"id":"2212.04136","title":"Design and Planning of Flexible Mobile Micro-Grids Using Deep Reinforcement Learning","created":"2022-12-08","cited_by_count":2,"area":null},{"id":"2212.06064","title":"Reinforcement Learning Applied to Trading Systems: A Survey","created":"2022-11-01","cited_by_count":2,"area":null},{"id":"2308.15550","title":"Adversarial Style Transfer for Robust Policy Optimization in Deep Reinforcement Learning","created":"2023-08-29","cited_by_count":2,"area":null},{"id":"2309.15242","title":"PlotMap: Automated Layout Design for Building Game Worlds","created":"2023-09-26","cited_by_count":2,"area":null},{"id":"2101.01883","title":"Off-Policy Meta-Reinforcement Learning Based on Feature Embedding Spaces","created":"2021-01-06","cited_by_count":1,"area":null},{"id":"2102.07266","title":"Sparse Attention Guided Dynamic Value Estimation for Single-Task Multi-Scene Reinforcement Learning","created":"2021-02-14","cited_by_count":1,"area":null},{"id":"2107.01347","title":"Traffic Signal Control with Communicative Deep Reinforcement Learning Agents: a Case Study","created":"2021-07-03","cited_by_count":1,"area":null},{"id":"2107.06195","title":"Transfer Learning in Multi-Agent Reinforcement Learning with Double Q-Networks for Distributed Resource Sharing in V2X Communication","created":"2021-07-13","cited_by_count":1,"area":null},{"id":"2111.08733","title":"Learning Provably Robust Motion Planners Using Funnel Libraries","created":"2021-11-16","cited_by_count":1,"area":null},{"id":"2210.02224","title":"Neural Distillation as a State Representation Bottleneck in Reinforcement Learning","created":"2022-10-05","cited_by_count":1,"area":null},{"id":"2301.05635","title":"Time-Myopic Go-Explore: Learning A State Representation for the Go-Explore Paradigm","created":"2023-01-13","cited_by_count":1,"area":null},{"id":"2307.05209","title":"Contextual Pre-planning on Reward Machine Abstractions for Enhanced Transfer in Deep Reinforcement Learning","created":"2023-07-11","cited_by_count":1,"area":null},{"id":"2310.10610","title":"Quantifying Assistive Robustness Via the Natural-Adversarial Frontier","created":"2023-10-16","cited_by_count":1,"area":null},{"id":"2311.07312","title":"C-Procgen: Empowering Procgen with Controllable Contexts","created":"2023-11-13","cited_by_count":1,"area":null},{"id":"2311.15960","title":"Program Machine Policy: Addressing Long-Horizon Tasks by Integrating Program Synthesis and State Machines","created":"2023-11-27","cited_by_count":1,"area":null},{"id":"2401.09258","title":"Efficient Training of Generalizable Visuomotor Policies via Control-Aware Augmentation","created":"2024-01-17","cited_by_count":1,"area":null},{"id":"2503.12406","title":"Bio-Inspired Plastic Neural Networks for Zero-Shot Out-of-Distribution Generalization in Complex Animal-Inspired Robots","created":"2025-03-16","cited_by_count":1,"area":null},{"id":"2505.17714","title":"PPO-BR: Dual-Signal Entropy-Reward Adaptation for Trust Region Policy Optimization","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2511.15002","title":"Task Specific Sharpness Aware O-RAN Resource Management using Multi Agent Reinforcement Learning","created":"2025-11-19","cited_by_count":1,"area":null},{"id":"2110.08066","title":"Dual-Arm Adversarial Robot Learning","created":"2021-10-15","cited_by_count":0,"area":null},{"id":"2112.00583","title":"Meta Arcade: A Configurable Environment Suite for Meta-Learning","created":"2021-12-01","cited_by_count":0,"area":null},{"id":"2201.01099","title":"Learning Complex Spatial Behaviours in ABM: An Experimental Observational Study","created":"2022-01-04","cited_by_count":0,"area":null},{"id":"2202.13549","title":"Machine Learning Empowered Intelligent Data Center Networking: A Survey","created":"2022-02-28","cited_by_count":0,"area":null},{"id":"2204.02210","title":"Model Based Meta Learning of Critics for Policy Gradients","created":"2022-04-05","cited_by_count":0,"area":null},{"id":"2204.14076","title":"Dynamic Noises of Multi-Agent Environments Can Improve Generalization: Agent-based Models meets Reinforcement Learning","created":"2022-03-26","cited_by_count":0,"area":null},{"id":"2209.09058","title":"Measuring Interventional Robustness in Reinforcement Learning","created":"2022-09-19","cited_by_count":0,"area":null},{"id":"2210.07312","title":"Bootstrap Advantage Estimation for Policy Optimization in Reinforcement Learning","created":"2022-10-13","cited_by_count":0,"area":null},{"id":"2302.06126","title":"Expediting Distributed DNN Training with Device Topology-Aware Graph Deployment","created":"2023-02-13","cited_by_count":0,"area":null},{"id":"2304.14533","title":"Adversarial Policy Optimization in Deep Reinforcement Learning","created":"2023-04-27","cited_by_count":0,"area":null},{"id":"2310.20654","title":"Closed Drafting as a Case Study for First-Principle Interpretability, Memory, and Generalizability in Deep Reinforcement Learning","created":"2023-10-31","cited_by_count":0,"area":null}],"next_cursor":"100"}