{"list":"other","total":56,"rows":[{"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":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1505.05770","title":"Variational Inference with Normalizing Flows","created":"2015-05-21","cited_by_count":2170},{"id":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1611.00712","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","created":"2016-11-02","cited_by_count":1148},{"id":"2305.13301","title":"Training Diffusion Models with Reinforcement Learning","created":"2023-05-22","cited_by_count":982},{"id":"1511.06581","title":"Dueling Network Architectures for Deep Reinforcement Learning","created":"2015-11-20","cited_by_count":785},{"id":"1702.08165","title":"Reinforcement Learning with Deep Energy-Based Policies","created":"2017-02-27","cited_by_count":669},{"id":"1606.01868","title":"Unifying Count-Based Exploration and Intrinsic Motivation","created":"2016-06-06","cited_by_count":639},{"id":"1805.00909","title":"Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review","created":"2018-05-02","cited_by_count":482},{"id":"2106.04399","title":"Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation","created":"2021-06-08","cited_by_count":392},{"id":"1806.02473","title":"Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation","created":"2018-06-07","cited_by_count":364},{"id":"2111.09266","title":"GFlowNet Foundations","created":"2021-11-17","cited_by_count":290},{"id":"1901.11275","title":"A Theory of Regularized Markov Decision Processes","created":"2019-01-31","cited_by_count":286},{"id":"1906.10652","title":"Monte Carlo Gradient Estimation in Machine Learning","created":"2019-06-25","cited_by_count":283},{"id":"2201.13259","title":"Trajectory balance: Improved credit assignment in GFlowNets","created":"2022-01-31","cited_by_count":251},{"id":"1702.08892","title":"Bridging the Gap Between Value and Policy Based Reinforcement Learning","created":"2017-02-28","cited_by_count":182},{"id":"2103.06257","title":"Maximum Entropy RL (Provably) Solves Some Robust RL Problems","created":"2021-03-10","cited_by_count":176},{"id":"1802.08665","title":"Learning Latent Permutations with Gumbel-Sinkhorn Networks","created":"2018-02-23","cited_by_count":175},{"id":"1910.07207","title":"Soft Actor-Critic for Discrete Action Settings","created":"2019-10-16","cited_by_count":174},{"id":"2203.04115","title":"Biological Sequence Design with GFlowNets","created":"2022-03-02","cited_by_count":174},{"id":"1704.06440","title":"Equivalence Between Policy Gradients and Soft Q-Learning","created":"2017-04-21","cited_by_count":173},{"id":"2202.13903","title":"Bayesian Structure Learning with Generative Flow Networks","created":"2022-02-28","cited_by_count":153},{"id":"2209.12782","title":"Learning GFlowNets from partial episodes for improved convergence and stability","created":"2022-09-26","cited_by_count":132},{"id":"1512.08562","title":"Taming the Noise in Reinforcement Learning via Soft Updates","created":"2015-12-28","cited_by_count":127},{"id":"2202.01361","title":"Generative Flow Networks for Discrete Probabilistic Modeling","created":"2022-02-03","cited_by_count":114},{"id":"2210.00580","title":"GFlowNets and variational inference","created":"2022-10-02","cited_by_count":106},{"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":"2310.04363","title":"Amortizing intractable inference in large language models","created":"2023-10-06","cited_by_count":97},{"id":"2302.01687","title":"Better Training of GFlowNets with Local Credit and Incomplete Trajectories","created":"2023-02-03","cited_by_count":85},{"id":"2301.13362","title":"Optimizing DDPM Sampling with Shortcut Fine-Tuning","created":"2023-01-31","cited_by_count":81},{"id":"2305.07170","title":"Towards Understanding and Improving GFlowNet Training","created":"2023-05-11","cited_by_count":75},{"id":"2302.05446","title":"Robust Scheduling with GFlowNets","created":"2023-01-17","cited_by_count":69},{"id":"2310.12934","title":"Generative Flow Networks as Entropy-Regularized RL","created":"2023-10-19","cited_by_count":64},{"id":"2302.00615","title":"GFlowNets for AI-Driven Scientific Discovery","created":"2023-02-01","cited_by_count":63},{"id":"1302.6808","title":"Learning Gaussian Networks","created":"2013-02-27","cited_by_count":62},{"id":"2305.19366","title":"Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Network","created":"2023-05-30","cited_by_count":50},{"id":"2302.06576","title":"GFlowNet-EM for learning compositional latent variable models","created":"2023-02-13","cited_by_count":40},{"id":"2305.17010","title":"Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNets","created":"2023-05-26","cited_by_count":40},{"id":"2210.07992","title":"A Variational Perspective on Generative Flow Networks","created":"2022-10-14","cited_by_count":39},{"id":"2302.09465","title":"Stochastic Generative Flow Networks","created":"2023-02-19","cited_by_count":32},{"id":"2306.17693","title":"Thompson sampling for improved exploration in GFlowNets","created":"2023-06-30","cited_by_count":32},{"id":"2310.04925","title":"Crystal-GFN: sampling crystals with desirable properties and constraints","created":"2023-10-07","cited_by_count":31},{"id":"2211.02763","title":"Bayesian learning of Causal Structure and Mechanisms with GFlowNets and Variational Bayes","created":"2022-11-04","cited_by_count":30},{"id":"2312.14331","title":"Maximum entropy GFlowNets with soft Q-learning","created":"2023-12-21","cited_by_count":30},{"id":"2310.08774","title":"PhyloGFN: Phylogenetic inference with generative flow networks","created":"2023-10-12","cited_by_count":22},{"id":"2303.02430","title":"CFlowNets: Continuous Control with Generative Flow Networks","created":"2023-03-04","cited_by_count":19},{"id":"2307.07674","title":"An Empirical Study of the Effectiveness of Using a Replay Buffer on Mode Discovery in GFlowNets","created":"2023-07-15","cited_by_count":18},{"id":"1506.03504","title":"Data Generation as Sequential Decision Making","created":"2015-06-10","cited_by_count":15},{"id":"2306.11715","title":"Multi-Fidelity Active Learning with GFlowNets","created":"2023-06-20","cited_by_count":15},{"id":"2310.02423","title":"Delta-AI: Local objectives for amortized inference in sparse graphical models","created":"2023-10-03","cited_by_count":7},{"id":"2310.02779","title":"Expected flow networks in stochastic environments and two-player zero-sum games","created":"2023-10-04","cited_by_count":7},{"id":"1910.06862","title":"Approximate Inference in Discrete Distributions with Monte Carlo Tree Search and Value Functions","created":"2019-10-15","cited_by_count":6},{"id":"2209.06259","title":"Designing Biological Sequences via Meta-Reinforcement Learning and Bayesian Optimization","created":"2022-09-13","cited_by_count":4}],"next_cursor":null}