{"list":"other","total":105,"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":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"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":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"1606.01540","title":"OpenAI Gym","created":"2016-06-05","cited_by_count":1736},{"id":"1609.03499","title":"WaveNet: A Generative Model for Raw Audio","created":"2016-09-12","cited_by_count":1722},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"1511.05952","title":"Prioritized Experience Replay","created":"2015-11-18","cited_by_count":1099},{"id":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055},{"id":"1707.06887","title":"A Distributional Perspective on Reinforcement Learning","created":"2017-07-21","cited_by_count":765},{"id":"1910.07113","title":"Solving Rubik's Cube with a Robot Hand","created":"2019-10-16","cited_by_count":734},{"id":"1702.08165","title":"Reinforcement Learning with Deep Energy-Based Policies","created":"2017-02-27","cited_by_count":669},{"id":"2209.14375","title":"Improving alignment of dialogue agents via targeted human judgements","created":"2022-09-28","cited_by_count":531},{"id":"1710.11248","title":"Learning Robust Rewards with Adversarial Inverse Reinforcement Learning","created":"2017-10-30","cited_by_count":490},{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447},{"id":"1805.11074","title":"Reward Constrained Policy Optimization","created":"2018-05-28","cited_by_count":417},{"id":"1611.05397","title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","created":"2016-11-16","cited_by_count":404},{"id":"2201.03544","title":"The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models","created":"2022-01-10","cited_by_count":328},{"id":"2306.08647","title":"Language to Rewards for Robotic Skill Synthesis","created":"2023-06-14","cited_by_count":312},{"id":"2106.05091","title":"PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training","created":"2021-06-09","cited_by_count":302},{"id":"1904.12901","title":"Challenges of Real-World Reinforcement Learning","created":"2019-04-29","cited_by_count":291},{"id":"1907.00456","title":"Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog","created":"2019-06-30","cited_by_count":284},{"id":"1708.04782","title":"StarCraft II: A New Challenge for Reinforcement Learning","created":"2017-08-16","cited_by_count":274},{"id":"2102.09548","title":"Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development","created":"2021-02-18","cited_by_count":264},{"id":"2303.00001","title":"Reward Design with Language Models","created":"2023-02-27","cited_by_count":261},{"id":"1904.06387","title":"Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations","created":"2019-04-12","cited_by_count":260},{"id":"1907.11180","title":"Google Research Football: A Novel Reinforcement Learning Environment","created":"2019-07-25","cited_by_count":260},{"id":"1801.08757","title":"Safe Exploration in Continuous Action Spaces","created":"2018-01-26","cited_by_count":247},{"id":"1810.08272","title":"BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning","created":"2018-10-18","cited_by_count":244},{"id":"1812.02690","title":"Provably Efficient Maximum Entropy Exploration","created":"2018-12-06","cited_by_count":242},{"id":"1809.02627","title":"Unity: A General Platform for Intelligent Agents","created":"2018-09-07","cited_by_count":236},{"id":"1809.02925","title":"Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning","created":"2018-09-09","cited_by_count":204},{"id":"2010.03152","title":"Projection-Based Constrained Policy Optimization","created":"2020-10-07","cited_by_count":203},{"id":"1611.03673","title":"Learning to Navigate in Complex Environments","created":"2016-11-11","cited_by_count":198},{"id":"1612.07182","title":"Multi-Agent Cooperation and the Emergence of (Natural) Language","created":"2016-12-21","cited_by_count":185},{"id":"1810.05587","title":"A Survey and Critique of Multiagent Deep Reinforcement Learning","created":"2018-10-12","cited_by_count":177},{"id":"1507.04888","title":"Maximum Entropy Deep Inverse Reinforcement Learning","created":"2015-07-17","cited_by_count":176},{"id":"1611.03852","title":"A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models","created":"2016-11-11","cited_by_count":168},{"id":"1906.03926","title":"A Survey of Reinforcement Learning Informed by Natural Language","created":"2019-06-10","cited_by_count":154},{"id":"1901.10031","title":"Lyapunov-based Safe Policy Optimization for Continuous Control","created":"2019-01-28","cited_by_count":145},{"id":"2209.12782","title":"Learning GFlowNets from partial episodes for improved convergence and stability","created":"2022-09-26","cited_by_count":132},{"id":"1711.01239","title":"Routing Networks: Adaptive Selection of Non-linear Functions for Multi-Task Learning","created":"2017-11-03","cited_by_count":126},{"id":"1610.03483","title":"Learning in Implicit Generative Models","created":"2016-10-11","cited_by_count":125},{"id":"1903.02020","title":"Using Natural Language for Reward Shaping in Reinforcement Learning","created":"2019-03-05","cited_by_count":114},{"id":"1910.01708","title":"Benchmarking Batch Deep Reinforcement Learning Algorithms","created":"2019-10-03","cited_by_count":111},{"id":"2210.00580","title":"GFlowNets and variational inference","created":"2022-10-02","cited_by_count":106},{"id":"1707.05173","title":"Trial without Error: Towards Safe Reinforcement Learning via Human Intervention","created":"2017-07-17","cited_by_count":103},{"id":"2310.00166","title":"Motif: Intrinsic Motivation from Artificial Intelligence Feedback","created":"2023-09-29","cited_by_count":102},{"id":"2210.12765","title":"Multi-Objective GFlowNets","created":"2022-10-23","cited_by_count":101},{"id":"2301.12594","title":"A theory of continuous generative flow networks","created":"2023-01-30","cited_by_count":101},{"id":"1812.02224","title":"Adapting Auxiliary Losses Using Gradient Similarity","created":"2018-12-05","cited_by_count":100},{"id":"2302.01687","title":"Better Training of GFlowNets with Local Credit and Incomplete Trajectories","created":"2023-02-03","cited_by_count":85},{"id":"1610.02707","title":"Multi-Objective Deep Reinforcement Learning","created":"2016-10-09","cited_by_count":83},{"id":"1806.01946","title":"Learning to Understand Goal Specifications by Modelling Reward","created":"2018-06-05","cited_by_count":80},{"id":"2006.12136","title":"Safe Reinforcement Learning via Curriculum Induction","created":"2020-06-22","cited_by_count":74},{"id":"1912.10944","title":"A Survey of Deep Reinforcement Learning in Video Games","created":"2019-12-23","cited_by_count":73},{"id":"2109.00157","title":"A Survey of Exploration Methods in Reinforcement Learning","created":"2021-09-01","cited_by_count":73},{"id":"1612.07307","title":"Loss is its own Reward: Self-Supervision for Reinforcement Learning","created":"2016-12-21","cited_by_count":72},{"id":"1804.05958","title":"Can Neural Machine Translation be Improved with User Feedback?","created":"2018-04-16","cited_by_count":72},{"id":"2302.05446","title":"Robust Scheduling with GFlowNets","created":"2023-01-17","cited_by_count":69},{"id":"1902.07742","title":"From Language to Goals: Inverse Reinforcement Learning for Vision-Based Instruction Following","created":"2019-02-20","cited_by_count":67},{"id":"1906.08928","title":"Learning Reward Functions by Integrating Human Demonstrations and Preferences","created":"2019-06-21","cited_by_count":64},{"id":"1802.06480","title":"Accelerated Primal-Dual Policy Optimization for Safe Reinforcement Learning","created":"2018-02-19","cited_by_count":62},{"id":"1902.06865","title":"Hyperbolic Discounting and Learning over Multiple Horizons","created":"2019-02-19","cited_by_count":60},{"id":"2106.12177","title":"Imitation Learning: Progress, Taxonomies and Challenges","created":"2021-06-23","cited_by_count":58},{"id":"2305.00955","title":"Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generation","created":"2023-05-01","cited_by_count":55},{"id":"2302.06576","title":"GFlowNet-EM for learning compositional latent variable models","created":"2023-02-13","cited_by_count":40},{"id":"2103.04847","title":"Adversarial Reinforcement Learning for Procedural Content Generation","created":"2021-03-08","cited_by_count":36},{"id":"1902.04623","title":"Value constrained model-free continuous control","created":"2019-02-12","cited_by_count":34},{"id":"1901.08492","title":"Feudal Multi-Agent Hierarchies for Cooperative Reinforcement Learning","created":"2019-01-24","cited_by_count":33},{"id":"2112.12228","title":"Direct Behavior Specification via Constrained Reinforcement Learning","created":"2021-12-22","cited_by_count":31},{"id":"1809.07124","title":"Pommerman: A Multi-Agent Playground","created":"2018-09-19","cited_by_count":30},{"id":"1811.08586","title":"Urban Driving with Multi-Objective Deep Reinforcement Learning","created":"2018-11-21","cited_by_count":30},{"id":"2211.07357","title":"Controlling Commercial Cooling Systems Using Reinforcement Learning","created":"2022-11-11","cited_by_count":29},{"id":"2011.04764","title":"Deep Reinforcement Learning for Navigation in AAA Video Games","created":"2020-11-09","cited_by_count":27},{"id":"2302.04178","title":"DynGFN: Towards Bayesian Inference of Gene Regulatory Networks with GFlowNets","created":"2023-02-08","cited_by_count":27},{"id":"1712.07893","title":"A Deep Policy Inference Q-Network for Multi-Agent Systems","created":"2017-12-21","cited_by_count":25},{"id":"1611.01626","title":"Combining policy gradient and Q-learning","created":"2016-11-05","cited_by_count":24},{"id":"1704.05539","title":"Beating Atari with Natural Language Guided Reinforcement Learning","created":"2017-04-18","cited_by_count":24},{"id":"2209.02606","title":"Unifying Generative Models with GFlowNets and Beyond","created":"2022-09-06","cited_by_count":24},{"id":"1903.09708","title":"Explaining Reinforcement Learning to Mere Mortals: An Empirical Study","created":"2019-03-22","cited_by_count":21},{"id":"2301.04741","title":"Efficient Preference-Based Reinforcement Learning Using Learned Dynamics Models","created":"2023-01-11","cited_by_count":21},{"id":"1704.06616","title":"Accurately and Efficiently Interpreting Human-Robot Instructions of Varying Granularities","created":"2017-04-21","cited_by_count":19},{"id":"2010.06324","title":"Balancing Constraints and Rewards with Meta-Gradient D4PG","created":"2020-10-13","cited_by_count":18},{"id":"2105.09637","title":"Navigation Turing Test (NTT): Learning to Evaluate Human-Like Navigation","created":"2021-05-20","cited_by_count":17},{"id":"2212.13769","title":"Lexicographic Multi-Objective Reinforcement Learning","created":"2022-12-28","cited_by_count":17},{"id":"1911.00497","title":"A Narration-based Reward Shaping Approach using Grounded Natural Language Commands","created":"2019-10-31","cited_by_count":16},{"id":"2309.03315","title":"Robotic Table Tennis: A Case Study into a High Speed Learning System","created":"2023-09-06","cited_by_count":13}],"next_cursor":"100"}