{"list":"other","total":51,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"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":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"1911.08265","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","created":"2019-11-19","cited_by_count":1353},{"id":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"id":"1801.00690","title":"DeepMind Control Suite","created":"2018-01-02","cited_by_count":956},{"id":"1710.02298","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","created":"2017-10-06","cited_by_count":786},{"id":"1511.06581","title":"Dueling Network Architectures for Deep Reinforcement Learning","created":"2015-11-20","cited_by_count":785},{"id":"2004.13649","title":"Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels","created":"2020-04-28","cited_by_count":585},{"id":"2310.16828","title":"TD-MPC2: Scalable, Robust World Models for Continuous Control","created":"2023-10-25","cited_by_count":512},{"id":"1710.10044","title":"Distributional Reinforcement Learning with Quantile Regression","created":"2017-10-27","cited_by_count":474},{"id":"1507.06527","title":"Deep Recurrent Q-Learning for Partially Observable MDPs","created":"2015-07-23","cited_by_count":465},{"id":"2107.09645","title":"Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning","created":"2021-07-20","cited_by_count":372},{"id":"1806.06923","title":"Implicit Quantile Networks for Distributional Reinforcement Learning","created":"2018-06-14","cited_by_count":369},{"id":"1806.06920","title":"Maximum a Posteriori Policy Optimisation","created":"2018-06-14","cited_by_count":328},{"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":"1706.10295","title":"Noisy Networks for Exploration","created":"2017-06-30","cited_by_count":266},{"id":"2212.13345","title":"The Forward-Forward Algorithm: Some Preliminary Investigations","created":"2022-12-27","cited_by_count":266},{"id":"1609.01596","title":"Direct Feedback Alignment Provides Learning in Deep Neural Networks","created":"2016-09-06","cited_by_count":240},{"id":"2111.00210","title":"Mastering Atari Games with Limited Data","created":"2021-10-30","cited_by_count":237},{"id":"1901.06656","title":"Training Neural Networks with Local Error Signals","created":"2019-01-20","cited_by_count":136},{"id":"1702.08887","title":"Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning","created":"2017-02-28","cited_by_count":117},{"id":"1812.11446","title":"Greedy Layerwise Learning Can Scale to ImageNet","created":"2018-12-29","cited_by_count":115},{"id":"2110.14555","title":"V-Learning -- A Simple, Efficient, Decentralized Algorithm for Multiagent RL","created":"2021-10-27","cited_by_count":114},{"id":"2202.08587","title":"Gradients without Backpropagation","created":"2022-02-17","cited_by_count":73},{"id":"2210.03310","title":"Scaling Forward Gradient With Local Losses","created":"2022-10-07","cited_by_count":65},{"id":"2111.02552","title":"Is Bang-Bang Control All You Need? Solving Continuous Control with Bernoulli Policies","created":"2021-11-03","cited_by_count":38},{"id":"1506.07924","title":"Decentralized Q-Learning for Stochastic Teams and Games","created":"2015-06-25","cited_by_count":35},{"id":"1707.04402","title":"Lenient Multi-Agent Deep Reinforcement Learning","created":"2017-07-14","cited_by_count":35},{"id":"2301.01452","title":"The Predictive Forward-Forward Algorithm","created":"2023-01-04","cited_by_count":35},{"id":"2306.06968","title":"Can Forward Gradient Match Backpropagation?","created":"2023-06-12","cited_by_count":26},{"id":"2312.12668","title":"Convolutional Channel-wise Competitive Learning for the Forward-Forward Algorithm","created":"2023-12-19","cited_by_count":25},{"id":"2210.12566","title":"Solving Continuous Control via Q-learning","created":"2022-10-22","cited_by_count":24},{"id":"2505.13124","title":"$\\mu$PC: Scaling Predictive Coding to 100+ Layer Networks","created":"2025-05-19","cited_by_count":15},{"id":"2305.18353","title":"Emergent representations in networks trained with the Forward-Forward algorithm","created":"2023-05-26","cited_by_count":11},{"id":"2310.04590","title":"Deep Model Predictive Optimization","created":"2023-10-06","cited_by_count":7},{"id":"2312.04709","title":"How to guess a gradient","created":"2023-12-07","cited_by_count":7},{"id":"2209.08244","title":"MA2QL: A Minimalist Approach to Fully Decentralized Multi-Agent Reinforcement Learning","created":"2022-09-17","cited_by_count":5},{"id":"2211.03032","title":"Decentralized Policy Optimization","created":"2022-11-06","cited_by_count":5},{"id":"2302.01188","title":"Best Possible Q-Learning","created":"2023-02-02","cited_by_count":4},{"id":"2411.03604","title":"Temporal-Difference Learning Using Distributed Error Signals","created":"2024-11-06","cited_by_count":3}],"next_cursor":null}