{"list":"other","total":71,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"2012.07436","title":"Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting","created":"2020-12-14","cited_by_count":2169},{"id":"1910.07467","title":"Root Mean Square Layer Normalization","created":"2019-10-16","cited_by_count":1480},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"1702.03118","title":"Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning","created":"2017-02-10","cited_by_count":950},{"id":"1503.05671","title":"Optimizing Neural Networks with Kronecker-factored Approximate Curvature","created":"2015-03-19","cited_by_count":796},{"id":"1710.02298","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","created":"2017-10-06","cited_by_count":786},{"id":"2006.12983","title":"dm_control: Software and Tasks for Continuous Control","created":"2020-06-22","cited_by_count":375},{"id":"2010.07468","title":"AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradients","created":"2020-10-15","cited_by_count":283},{"id":"1706.10295","title":"Noisy Networks for Exploration","created":"2017-06-30","cited_by_count":266},{"id":"1911.07013","title":"Understanding and Improving Layer Normalization","created":"2019-11-16","cited_by_count":217},{"id":"2005.12729","title":"Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO","created":"2020-05-25","cited_by_count":186},{"id":"2303.01486","title":"Understanding plasticity in neural networks","created":"2023-03-02","cited_by_count":174},{"id":"2006.05990","title":"What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study","created":"2020-06-10","cited_by_count":162},{"id":"2206.15472","title":"On-Device Training Under 256KB Memory","created":"2022-06-30","cited_by_count":160},{"id":"2305.19452","title":"Bigger, Better, Faster: Human-level Atari with human-level efficiency","created":"2023-05-30","cited_by_count":147},{"id":"2304.13653","title":"Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning","created":"2023-04-26","cited_by_count":133},{"id":"2204.09560","title":"Understanding and Preventing Capacity Loss in Reinforcement Learning","created":"2022-04-20","cited_by_count":125},{"id":"2303.07507","title":"Loss of Plasticity in Continual Deep Reinforcement Learning","created":"2023-03-13","cited_by_count":121},{"id":"1503.04269","title":"An Emphatic Approach to the Problem of Off-policy Temporal-Difference Learning","created":"2015-03-14","cited_by_count":103},{"id":"1602.07714","title":"Learning values across many orders of magnitude","created":"2016-02-24","cited_by_count":85},{"id":"1712.00378","title":"Time Limits in Reinforcement Learning","created":"2017-12-01","cited_by_count":79},{"id":"2104.04132","title":"Replay in Deep Learning: Current Approaches and Missing Biological Elements","created":"2021-04-01","cited_by_count":72},{"id":"2403.00514","title":"Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning","created":"2024-03-01","cited_by_count":50},{"id":"2404.00781","title":"Addressing Loss of Plasticity and Catastrophic Forgetting in Continual Learning","created":"2024-03-31","cited_by_count":50},{"id":"2106.04217","title":"Dynamic Sparse Training for Deep Reinforcement Learning","created":"2021-06-08","cited_by_count":49},{"id":"2203.10681","title":"Online Continual Learning for Embedded Devices","created":"2022-03-21","cited_by_count":49},{"id":"2406.02596","title":"Slow and Steady Wins the Race: Maintaining Plasticity with Hare and Tortoise Networks","created":"2024-06-01","cited_by_count":43},{"id":"1906.07073","title":"Is the Policy Gradient a Gradient?","created":"2019-06-17","cited_by_count":40},{"id":"2403.19076","title":"Tiny Machine Learning: Progress and Futures","created":"2024-03-28","cited_by_count":40},{"id":"2406.06811","title":"Learning Continually by Spectral Regularization","created":"2024-06-10","cited_by_count":34},{"id":"2110.11222","title":"Is High Variance Unavoidable in RL? A Case Study in Continuous Control","created":"2021-10-21","cited_by_count":28},{"id":"2310.07418","title":"Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages","created":"2023-10-11","cited_by_count":28},{"id":"2007.01839","title":"Expected Eligibility Traces","created":"2020-07-03","cited_by_count":27},{"id":"2306.17833","title":"Resetting the Optimizer in Deep RL: An Empirical Study","created":"2023-06-30","cited_by_count":26},{"id":"2305.15947","title":"Online learning of long-range dependencies","created":"2023-05-25","cited_by_count":25},{"id":"1811.06626","title":"The Utility of Sparse Representations for Control in Reinforcement Learning","created":"2018-11-15","cited_by_count":24},{"id":"2102.09407","title":"Adaptive Rational Activations to Boost Deep Reinforcement Learning","created":"2021-02-18","cited_by_count":23},{"id":"2105.05347","title":"Return-based Scaling: Yet Another Normalisation Trick for Deep RL","created":"2021-05-11","cited_by_count":23},{"id":"2203.12759","title":"Asynchronous Reinforcement Learning for Real-Time Control of Physical Robots","created":"2022-03-23","cited_by_count":22},{"id":"1607.00446","title":"A Greedy Approach to Adapting the Trace Parameter for Temporal Difference Learning","created":"2016-07-02","cited_by_count":20},{"id":"2212.00824","title":"On-device Training: A First Overview on Existing Systems","created":"2022-12-01","cited_by_count":19},{"id":"2305.19044","title":"Exploring the Promise and Limits of Real-Time Recurrent Learning","created":"2023-05-30","cited_by_count":19},{"id":"1710.01329","title":"Improving Lexical Choice in Neural Machine Translation","created":"2017-10-03","cited_by_count":17},{"id":"2003.07417","title":"Improving Performance in Reinforcement Learning by Breaking Generalization in Neural Networks","created":"2020-03-16","cited_by_count":17},{"id":"2205.05748","title":"Tiny Robot Learning: Challenges and Directions for Machine Learning in Resource-Constrained Robots","created":"2022-05-11","cited_by_count":17},{"id":"1512.04087","title":"True Online Temporal-Difference Learning","created":"2015-12-13","cited_by_count":16},{"id":"2011.04590","title":"From Eye-blinks to State Construction: Diagnostic Benchmarks for Online Representation Learning","created":"2020-11-09","cited_by_count":13},{"id":"2210.02317","title":"Real-Time Reinforcement Learning for Vision-Based Robotics Utilizing Local and Remote Computers","created":"2022-10-05","cited_by_count":13},{"id":"2312.01624","title":"GVFs in the Real World: Making Predictions Online for Water Treatment","created":"2023-12-04","cited_by_count":13},{"id":"2302.05326","title":"Scalable Real-Time Recurrent Learning Using Columnar-Constructive Networks","created":"2023-01-20","cited_by_count":11},{"id":"1907.07751","title":"Meta-descent for Online, Continual Prediction","created":"2019-07-17","cited_by_count":10},{"id":"2010.01069","title":"A Deeper Look at Discounting Mismatch in Actor-Critic Algorithms","created":"2020-10-02","cited_by_count":10},{"id":"2310.01365","title":"Elephant Neural Networks: Born to Be a Continual Learner","created":"2023-10-02","cited_by_count":10},{"id":"2202.11133","title":"Continual Auxiliary Task Learning","created":"2022-02-22","cited_by_count":9},{"id":"2306.13284","title":"Correcting discount-factor mismatch in on-policy policy gradient methods","created":"2023-06-23","cited_by_count":9},{"id":"1704.05495","title":"Investigating Recurrence and Eligibility Traces in Deep Q-Networks","created":"2017-04-18","cited_by_count":8},{"id":"2010.13083","title":"How to Make Deep RL Work in Practice","created":"2020-10-25","cited_by_count":8},{"id":"2106.06508","title":"Preferential Temporal Difference Learning","created":"2021-06-11","cited_by_count":6},{"id":"2402.02342","title":"MetaOptimize: A Framework for Optimizing Step Sizes and Other Meta-parameters","created":"2024-02-04","cited_by_count":5},{"id":"2406.03276","title":"Revisiting Scalable Hessian Diagonal Approximations for Applications in Reinforcement Learning","created":"2024-06-05","cited_by_count":5},{"id":"2211.07805","title":"Agent-State Construction with Auxiliary Inputs","created":"2022-11-15","cited_by_count":3},{"id":"2311.02215","title":"Towards model-free RL algorithms that scale well with unstructured data","created":"2023-11-03","cited_by_count":3},{"id":"1905.09562","title":"Recurrent Value Functions","created":"2019-05-23","cited_by_count":2}],"next_cursor":null}