{"total":45,"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":"2105.05246","title":"Spectral Normalisation for Deep Reinforcement Learning: an Optimisation Perspective","created":"2021-05-11","cited_by_count":65,"area":null},{"id":"2206.01626","title":"Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress","created":"2022-06-03","cited_by_count":65,"area":null},{"id":"2205.00329","title":"Continual Learning with Foundation Models: An Empirical Study of Latent Replay","created":"2022-04-30","cited_by_count":61,"area":null},{"id":"2306.01324","title":"Hyperparameters in Reinforcement Learning and How To Tune Them","created":"2023-06-02","cited_by_count":59,"area":null},{"id":"2304.01315","title":"Empirical Design in Reinforcement Learning","created":"2023-04-03","cited_by_count":55,"area":null},{"id":"2303.17503","title":"Pgx: Hardware-Accelerated Parallel Game Simulators for Reinforcement Learning","created":"2023-03-29","cited_by_count":51,"area":null},{"id":"2210.02019","title":"Atari-5: Distilling the Arcade Learning Environment down to Five Games","created":"2022-10-05","cited_by_count":44,"area":null},{"id":"2106.08229","title":"MICo: Improved representations via sampling-based state similarity for Markov decision processes","created":"2021-06-03","cited_by_count":43,"area":null},{"id":"2310.03882","title":"Small batch deep reinforcement learning","created":"2023-10-05","cited_by_count":36,"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":"2105.01648","title":"On Lottery Tickets and Minimal Task Representations in Deep Reinforcement Learning","created":"2021-05-04","cited_by_count":24,"area":null},{"id":"2102.09407","title":"Adaptive Rational Activations to Boost Deep Reinforcement Learning","created":"2021-02-18","cited_by_count":23,"area":null},{"id":"2208.10483","title":"Prioritizing Samples in Reinforcement Learning with Reducible Loss","created":"2022-08-22","cited_by_count":22,"area":null},{"id":"2204.00484","title":"Proper Reuse of Image Classification Features Improves Object Detection","created":"2022-04-01","cited_by_count":20,"area":null},{"id":"2312.12065","title":"PPO-Clip Attains Global Optimality: Towards Deeper Understandings of Clipping","created":"2023-12-19","cited_by_count":17,"area":null},{"id":"2110.01528","title":"Large Batch Experience Replay","created":"2021-10-04","cited_by_count":14,"area":null},{"id":"2207.11569","title":"Robots Enact Malignant Stereotypes","created":"2022-07-23","cited_by_count":14,"area":null},{"id":"2103.02886","title":"Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddings","created":"2021-03-04","cited_by_count":12,"area":null},{"id":"2307.05979","title":"Transformers in Reinforcement Learning: A Survey","created":"2023-07-12","cited_by_count":12,"area":null},{"id":"2305.01645","title":"Distill or Annotate? Cost-Efficient Fine-Tuning of Compact Models","created":"2023-05-02","cited_by_count":11,"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":"2308.00031","title":"Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challenges","created":"2023-07-31","cited_by_count":10,"area":null},{"id":"2106.15883","title":"Tuning Mixed Input Hyperparameters on the Fly for Efficient Population Based AutoRL","created":"2021-06-30","cited_by_count":8,"area":null},{"id":"2205.08464","title":"Robust Losses for Learning Value Functions","created":"2022-05-17","cited_by_count":7,"area":null},{"id":"2205.08716","title":"No More Pesky Hyperparameters: Offline Hyperparameter Tuning for RL","created":"2022-05-18","cited_by_count":6,"area":null},{"id":"2210.08153","title":"CUP: Critic-Guided Policy Reuse","created":"2022-10-15","cited_by_count":6,"area":null},{"id":"2112.04123","title":"ShinRL: A Library for Evaluating RL Algorithms from Theoretical and Practical Perspectives","created":"2021-12-08","cited_by_count":5,"area":null},{"id":"2210.03325","title":"Elastic Step DQN: A novel multi-step algorithm to alleviate overestimation in Deep QNetworks","created":"2022-10-07","cited_by_count":5,"area":null},{"id":"2107.07741","title":"When does loss-based prioritization fail?","created":"2021-07-16","cited_by_count":4,"area":null},{"id":"2110.13799","title":"Neural PPO-Clip Attains Global Optimality: A Hinge Loss Perspective","created":"2021-10-26","cited_by_count":4,"area":null},{"id":"2206.08781","title":"Reinforcement Learning for Economic Policy: A New Frontier?","created":"2022-06-16","cited_by_count":4,"area":null},{"id":"2209.14513","title":"How Does Return Distribution in Distributional Reinforcement Learning Help Optimization?","created":"2022-09-29","cited_by_count":4,"area":null},{"id":"2210.00882","title":"MSRL: Distributed Reinforcement Learning with Dataflow Fragments","created":"2022-10-03","cited_by_count":4,"area":null},{"id":"2212.10876","title":"Hyperparameters in Contextual RL are Highly Situational","created":"2022-12-21","cited_by_count":4,"area":null},{"id":"2310.19919","title":"Meta-Learning Strategies through Value Maximization in Neural Networks","created":"2023-10-30","cited_by_count":4,"area":null},{"id":"2106.03228","title":"Distributional Reinforcement Learning with Unconstrained Monotonic Neural Networks","created":"2021-06-06","cited_by_count":3,"area":null},{"id":"2110.02639","title":"On The Transferability of Deep-Q Networks","created":"2021-10-06","cited_by_count":3,"area":null},{"id":"2412.06333","title":"Augmenting the action space with conventions to improve multi-agent cooperation in Hanabi","created":"2024-12-09","cited_by_count":2,"area":null},{"id":"2212.03865","title":"Learning on Graphs for Mineral Asset Valuation Under Supply and Demand Uncertainty","created":"2022-12-07","cited_by_count":1,"area":null},{"id":"2212.05237","title":"Coordinate Ascent for Off-Policy RL with Global Convergence Guarantees","created":"2022-12-10","cited_by_count":1,"area":null},{"id":"2308.07351","title":"IOB: Integrating Optimization Transfer and Behavior Transfer for Multi-Policy Reuse","created":"2023-08-14","cited_by_count":1,"area":null},{"id":"2310.17173","title":"DSAC-C: Constrained Maximum Entropy for Robust Discrete Soft-Actor Critic","created":"2023-10-26","cited_by_count":0,"area":null}],"next_cursor":null}