{"total":36,"rows":[{"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":"2212.04458","title":"General-Purpose In-Context Learning by Meta-Learning Transformers","created":"2022-12-08","cited_by_count":105,"area":null},{"id":"2301.03044","title":"A Survey on Transformers in Reinforcement Learning","created":"2023-01-08","cited_by_count":50,"area":null},{"id":"2211.11260","title":"Discovering Evolution Strategies via Meta-Black-Box Optimization","created":"2022-11-21","cited_by_count":44,"area":null},{"id":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36,"area":null},{"id":"2304.03995","title":"Discovering Attention-Based Genetic Algorithms via Meta-Black-Box Optimization","created":"2023-04-08","cited_by_count":33,"area":null},{"id":"2110.06206","title":"StARformer: Transformer with State-Action-Reward Representations for Visual Reinforcement Learning","created":"2021-10-12","cited_by_count":27,"area":null},{"id":"2203.05960","title":"Policy Architectures for Compositional Generalization in Control","created":"2022-03-10","cited_by_count":23,"area":null},{"id":"2312.10975","title":"Inducing Point Operator Transformer: A Flexible and Scalable Architecture for Solving PDEs","created":"2023-12-18","cited_by_count":18,"area":null},{"id":"2208.03374","title":"Learning to Generalize with Object-centric Agents in the Open World Survival Game Crafter","created":"2022-08-05","cited_by_count":13,"area":null},{"id":"2209.09845","title":"Relational Reasoning via Set Transformers: Provable Efficiency and Applications to MARL","created":"2022-09-20","cited_by_count":12,"area":null},{"id":"2205.06806","title":"Goal-Guided Neural Cellular Automata: Learning to Control Self-Organising Systems","created":"2022-04-25","cited_by_count":9,"area":null},{"id":"2403.02985","title":"Evolution Transformer: In-Context Evolutionary Optimization","created":"2024-03-05","cited_by_count":9,"area":null},{"id":"2205.07868","title":"Minimal Neural Network Models for Permutation Invariant Agents","created":"2022-05-12","cited_by_count":4,"area":null},{"id":"2410.13166","title":"An Evolved Universal Transformer Memory","created":"2024-10-17","cited_by_count":4,"area":null},{"id":"2211.06665","title":"A Survey on Explainable Reinforcement Learning: Concepts, Algorithms, Challenges","created":"2022-11-12","cited_by_count":3,"area":null},{"id":"2212.01498","title":"Policy Learning for Active Target Tracking over Continuous SE(3) Trajectories","created":"2022-12-03","cited_by_count":3,"area":null},{"id":"2305.10449","title":"Cooperation Is All You Need","created":"2023-05-16","cited_by_count":3,"area":null},{"id":"2506.08630","title":"Shared Modular Recurrence in Contextual MDPs for Universal Morphology Control","created":"2025-06-10","cited_by_count":3,"area":null},{"id":"2211.15136","title":"Collective Intelligence for 2D Push Manipulations with Mobile Robots","created":"2022-11-28","cited_by_count":2,"area":null},{"id":"2407.04513","title":"LayerShuffle: Enhancing Robustness in Vision Transformers by Randomizing Layer Execution Order","created":"2024-07-05","cited_by_count":2,"area":null},{"id":"2502.02190","title":"Discovering Quality-Diversity Algorithms via Meta-Black-Box Optimization","created":"2025-02-04","cited_by_count":2,"area":null},{"id":"2109.08236","title":"Reinforcement Learning on Encrypted Data","created":"2021-09-16","cited_by_count":1,"area":null},{"id":"2204.11897","title":"Reinforcement Teaching","created":"2022-04-25","cited_by_count":1,"area":null},{"id":"2210.07329","title":"Sample Efficient Dynamics Learning for Symmetrical Legged Robots:Leveraging Physics Invariance and Geometric Symmetries","created":"2022-10-13","cited_by_count":1,"area":null},{"id":"2304.11524","title":"Personalized Federated Learning via Gradient Modulation for Heterogeneous Text Summarization","created":"2023-04-23","cited_by_count":1,"area":null},{"id":"2306.05727","title":"The Role of Diverse Replay for Generalisation in Reinforcement Learning","created":"2023-06-09","cited_by_count":1,"area":null},{"id":"2311.00441","title":"Improving Robustness for Vision Transformer with a Simple Dynamic Scanning Augmentation","created":"2023-11-01","cited_by_count":1,"area":null},{"id":"2410.03565","title":"Training on Irrelevant States Implies Data Augmentation: Generalization in Contextual MDPs","created":"2024-10-04","cited_by_count":1,"area":null},{"id":"2210.03850","title":"Information Topology","created":"2022-10-07","cited_by_count":0,"area":null},{"id":"2310.04159","title":"Amortized Network Intervention to Steer the Excitatory Point Processes","created":"2023-10-06","cited_by_count":0,"area":null},{"id":"2404.05484","title":"What is Intelligence? A Cycle Closure Perspective","created":"2024-04-08","cited_by_count":0,"area":null},{"id":"2407.12789","title":"Generalisation to unseen topologies: Towards control of biological neural network activity","created":"2024-06-17","cited_by_count":0,"area":null},{"id":"2507.12473","title":"The Generalist Brain Module: Module Repetition in Neural Networks in Light of the Minicolumn Hypothesis","created":"2025-07-01","cited_by_count":0,"area":null},{"id":"2604.01843","title":"Investigating Permutation-Invariant Discrete Representation Learning for Spatially Aligned Images","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2606.13970","title":"An Attention-based Model for Robust Forecasting with Missing Modality","created":"2026-06-11","cited_by_count":0,"area":null}],"next_cursor":null}