{"total":25,"rows":[{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807,"area":null},{"id":"2305.19452","title":"Bigger, Better, Faster: Human-level Atari with human-level efficiency","created":"2023-05-30","cited_by_count":147,"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":"2301.03044","title":"A Survey on Transformers in Reinforcement Learning","created":"2023-01-08","cited_by_count":50,"area":null},{"id":"2102.07920","title":"Training Larger Networks for Deep Reinforcement Learning","created":"2021-02-16","cited_by_count":38,"area":null},{"id":"2110.10809","title":"Hierarchical Skills for Efficient Exploration","created":"2021-10-20","cited_by_count":38,"area":null},{"id":"2106.06842","title":"Recomposing the Reinforcement Learning Building Blocks with Hypernetworks","created":"2021-06-12","cited_by_count":35,"area":null},{"id":"2305.18246","title":"Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo","created":"2023-05-29","cited_by_count":29,"area":null},{"id":"2203.05960","title":"Policy Architectures for Compositional Generalization in Control","created":"2022-03-10","cited_by_count":23,"area":null},{"id":"2101.01857","title":"Reinforcement Learning with Latent Flow","created":"2021-01-06","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":"2206.04672","title":"Overcoming the Spectral Bias of Neural Value Approximation","created":"2022-06-09","cited_by_count":19,"area":null},{"id":"2112.03257","title":"Functional Regularization for Reinforcement Learning via Learned Fourier Features","created":"2021-12-06","cited_by_count":17,"area":null},{"id":"2111.10247","title":"Fast and Data-Efficient Training of Rainbow: an Experimental Study on Atari","created":"2021-11-19","cited_by_count":10,"area":null},{"id":"2311.04060","title":"Estimator-Coupled Reinforcement Learning for Robust Purely Tactile In-Hand Manipulation","created":"2023-11-07","cited_by_count":9,"area":null},{"id":"2212.14538","title":"Transformer in Transformer as Backbone for Deep Reinforcement Learning","created":"2022-12-30","cited_by_count":6,"area":null},{"id":"2312.15863","title":"PDiT: Interleaving Perception and Decision-making Transformers for Deep Reinforcement Learning","created":"2023-12-26","cited_by_count":5,"area":null},{"id":"2310.00077","title":"Optimizing with Low Budgets: a Comparison on the Black-box Optimization Benchmarking Suite and OpenAI Gym","created":"2023-09-29","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":"2107.12942","title":"Reinforcement Learning with Formal Performance Metrics for Quadcopter Attitude Control under Non-nominal Contexts","created":"2021-07-27","cited_by_count":3,"area":null},{"id":"2210.14685","title":"Leveraging Demonstrations with Latent Space Priors","created":"2022-10-26","cited_by_count":3,"area":null},{"id":"2307.15621","title":"Shrink-Perturb Improves Architecture Mixing during Population Based Training for Neural Architecture Search","created":"2023-07-28","cited_by_count":2,"area":null},{"id":"2311.07822","title":"A Central Motor System Inspired Pre-training Reinforcement Learning for Robotic Control","created":"2023-11-14","cited_by_count":0,"area":null},{"id":"2601.14776","title":"M2I2HA: Multi-modal Object Detection Based on Intra- and Inter-Modal Hypergraph Attention","created":"2026-01-21","cited_by_count":0,"area":null},{"id":"2610.05936","title":"Combining Improvements in Uplink AI-RAN","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}