{"list":"other","total":57,"rows":[{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"1606.01540","title":"OpenAI Gym","created":"2016-06-05","cited_by_count":1736},{"id":"1710.03740","title":"Mixed Precision Training","created":"2017-10-10","cited_by_count":1156},{"id":"1910.07113","title":"Solving Rubik's Cube with a Robot Hand","created":"2019-10-16","cited_by_count":734},{"id":"2002.00444","title":"Deep Reinforcement Learning for Autonomous Driving: A Survey","created":"2020-02-02","cited_by_count":721},{"id":"1609.07061","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","created":"2016-09-22","cited_by_count":426},{"id":"1905.03696","title":"HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision","created":"2019-04-29","cited_by_count":402},{"id":"1610.03295","title":"Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving","created":"2016-10-11","cited_by_count":311},{"id":"1908.08796","title":"Reinforcement Learning in Healthcare: A Survey","created":"2019-08-22","cited_by_count":310},{"id":"2011.09533","title":"Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?","created":"2020-11-18","cited_by_count":294},{"id":"1708.04782","title":"StarCraft II: A New Challenge for Reinforcement Learning","created":"2017-08-16","cited_by_count":274},{"id":"2203.01387","title":"A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problems","created":"2022-03-02","cited_by_count":231},{"id":"2205.10330","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","created":"2022-05-20","cited_by_count":181},{"id":"1901.09504","title":"Improving Neural Network Quantization without Retraining using Outlier Channel Splitting","created":"2019-01-28","cited_by_count":151},{"id":"2006.00979","title":"Acme: A Research Framework for Distributed Reinforcement Learning","created":"2020-06-01","cited_by_count":146},{"id":"2010.09776","title":"SMARTS: Scalable Multi-Agent Reinforcement Learning Training School for Autonomous Driving","created":"2020-10-19","cited_by_count":121},{"id":"2006.03041","title":"Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction","created":"2020-06-04","cited_by_count":95},{"id":"2108.11887","title":"Federated Reinforcement Learning: Techniques, Applications, and Open Challenges","created":"2021-08-26","cited_by_count":81},{"id":"1812.10613","title":"Generative Adversarial User Model for Reinforcement Learning Based Recommendation System","created":"2018-12-27","cited_by_count":64},{"id":"1911.04175","title":"Multi-Agent Connected Autonomous Driving using Deep Reinforcement Learning","created":"2019-11-11","cited_by_count":53},{"id":"2102.11492","title":"DeepThermal: Combustion Optimization for Thermal Power Generating Units Using Offline Reinforcement Learning","created":"2021-02-23","cited_by_count":48},{"id":"2305.01738","title":"Leveraging Factored Action Spaces for Efficient Offline Reinforcement Learning in Healthcare","created":"2023-05-02","cited_by_count":42},{"id":"1803.02811","title":"Accelerated Methods for Deep Reinforcement Learning","created":"2018-03-07","cited_by_count":40},{"id":"2305.10697","title":"The Blessing of Heterogeneity in Federated Q-Learning: Linear Speedup and Beyond","created":"2023-05-18","cited_by_count":36},{"id":"1705.04862","title":"Efficient Parallel Methods for Deep Reinforcement Learning","created":"2017-05-13","cited_by_count":32},{"id":"2012.03112","title":"A Modern Primer on Processing in Memory","created":"2020-12-05","cited_by_count":32},{"id":"1809.05188","title":"CM3: Cooperative Multi-goal Multi-stage Multi-agent Reinforcement Learning","created":"2018-09-13","cited_by_count":31},{"id":"2109.14320","title":"Google Neural Network Models for Edge Devices: Analyzing and Mitigating Machine Learning Inference Bottlenecks","created":"2021-09-29","cited_by_count":23},{"id":"2111.11743","title":"Independent Learning in Stochastic Games","created":"2021-11-23","cited_by_count":22},{"id":"1903.03988","title":"Processing Data Where It Makes Sense: Enabling In-Memory Computation","created":"2019-03-10","cited_by_count":21},{"id":"2302.10418","title":"MAC-PO: Multi-Agent Experience Replay via Collective Priority Optimization","created":"2023-02-21","cited_by_count":20},{"id":"1910.01055","title":"QuaRL: Quantization for Fast and Environmentally Sustainable Reinforcement Learning","created":"2019-10-02","cited_by_count":19},{"id":"2109.12021","title":"Pythia: A Customizable Hardware Prefetching Framework Using Online Reinforcement Learning","created":"2021-09-24","cited_by_count":18},{"id":"2308.00846","title":"Pathfinding Future PIM Architectures by Demystifying a Commercial PIM Technology","created":"2023-08-01","cited_by_count":14},{"id":"2110.01709","title":"Benchmarking Memory-Centric Computing Systems: Analysis of Real Processing-in-Memory Hardware","created":"2021-10-04","cited_by_count":13},{"id":"2205.07394","title":"Sibyl: Adaptive and Extensible Data Placement in Hybrid Storage Systems Using Online Reinforcement Learning","created":"2022-05-15","cited_by_count":8},{"id":"2310.09385","title":"PIM-GPT: A Hybrid Process-in-Memory Accelerator for Autoregressive Transformers","created":"2023-10-13","cited_by_count":8},{"id":"2401.14428","title":"The Landscape of Compute-near-memory and Compute-in-memory: A Research and Commercial Overview","created":"2024-01-24","cited_by_count":8},{"id":"2306.00187","title":"AccMER: Accelerating Multi-Agent Experience Replay with Cache Locality-aware Prioritization","created":"2023-05-31","cited_by_count":7},{"id":"1905.09673","title":"Deep Q-Learning with Q-Matrix Transfer Learning for Novel Fire Evacuation Environment","created":"2019-05-23","cited_by_count":6},{"id":"1905.09822","title":"In-DRAM Bulk Bitwise Execution Engine","created":"2019-05-23","cited_by_count":6},{"id":"2302.05007","title":"Scalability Bottlenecks in Multi-Agent Reinforcement Learning Systems","created":"2023-02-10","cited_by_count":6},{"id":"1803.04783","title":"A Scalable Near-Memory Architecture for Training Deep Neural Networks on Large In-Memory Datasets","created":"2018-02-19","cited_by_count":5},{"id":"2208.01243","title":"A Framework for High-throughput Sequence Alignment using Real Processing-in-Memory Systems","created":"2022-08-02","cited_by_count":5},{"id":"2209.08938","title":"Accelerating Neural Network Inference with Processing-in-DRAM: From the Edge to the Cloud","created":"2022-09-19","cited_by_count":5},{"id":"2301.07486","title":"CINM (Cinnamon): A Compilation Infrastructure for Heterogeneous Compute In-Memory and Compute Near-Memory Paradigms","created":"2022-12-25","cited_by_count":5},{"id":"2310.01893","title":"SimplePIM: A Software Framework for Productive and Efficient Processing-in-Memory","created":"2023-10-03","cited_by_count":5},{"id":"2404.07164","title":"PIM-Opt: Demystifying Distributed Optimization Algorithms on a Real-World Processing-In-Memory System","created":"2024-04-10","cited_by_count":5},{"id":"2204.02085","title":"High-throughput Pairwise Alignment with the Wavefront Algorithm using Processing-in-Memory","created":"2022-04-05","cited_by_count":4},{"id":"2206.06022","title":"Machine Learning Training on a Real Processing-in-Memory System","created":"2022-06-13","cited_by_count":4},{"id":"2305.13411","title":"Towards Efficient Multi-Agent Learning Systems","created":"2023-05-22","cited_by_count":4},{"id":"1812.11473","title":"ORIGAMI: A Heterogeneous Split Architecture for In-Memory Acceleration of Learning","created":"2018-12-30","cited_by_count":3},{"id":"2402.16731","title":"PyGim: An Efficient Graph Neural Network Library for Real Processing-In-Memory Architectures","created":"2024-02-26","cited_by_count":3},{"id":"2404.08871","title":"PID-Comm: A Fast and Flexible Collective Communication Framework for Commodity Processing-in-DIMM Devices","created":"2024-04-13","cited_by_count":3},{"id":"2403.10051","title":"Accelerating Regular Path Queries over Graph Database with Processing-in-Memory","created":"2024-03-15","cited_by_count":1}],"next_cursor":null}