{"list":"other","total":52,"rows":[{"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":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"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":"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":"1505.05770","title":"Variational Inference with Normalizing Flows","created":"2015-05-21","cited_by_count":2170},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"1511.05952","title":"Prioritized Experience Replay","created":"2015-11-18","cited_by_count":1099},{"id":"1511.06581","title":"Dueling Network Architectures for Deep Reinforcement Learning","created":"2015-11-20","cited_by_count":785},{"id":"1805.12114","title":"Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models","created":"2018-05-30","cited_by_count":774},{"id":"1906.08253","title":"When to Trust Your Model: Model-Based Policy Optimization","created":"2019-06-19","cited_by_count":773},{"id":"1707.06887","title":"A Distributional Perspective on Reinforcement Learning","created":"2017-07-21","cited_by_count":765},{"id":"1509.09292","title":"Convolutional Networks on Graphs for Learning Molecular Fingerprints","created":"2015-09-30","cited_by_count":754},{"id":"1811.06128","title":"Machine Learning for Combinatorial Optimization: a Methodological Tour d'Horizon","created":"2018-11-15","cited_by_count":623},{"id":"1611.09940","title":"Neural Combinatorial Optimization with Reinforcement Learning","created":"2016-11-29","cited_by_count":608},{"id":"1903.00374","title":"Model-Based Reinforcement Learning for Atari","created":"2019-03-01","cited_by_count":502},{"id":"1710.10044","title":"Distributional Reinforcement Learning with Quantile Regression","created":"2017-10-27","cited_by_count":474},{"id":"1705.08551","title":"Safe Model-based Reinforcement Learning with Stability Guarantees","created":"2017-05-23","cited_by_count":366},{"id":"1806.02473","title":"Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation","created":"2018-06-07","cited_by_count":364},{"id":"1708.02596","title":"Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning","created":"2017-08-08","cited_by_count":297},{"id":"1811.09621","title":"GuacaMol: Benchmarking Models for De Novo Molecular Design","created":"2018-11-22","cited_by_count":297},{"id":"1811.12823","title":"Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models","created":"2018-11-29","cited_by_count":275},{"id":"1704.07555","title":"Molecular De Novo Design through Deep Reinforcement Learning","created":"2017-04-25","cited_by_count":267},{"id":"1802.10592","title":"Model-Ensemble Trust-Region Policy Optimization","created":"2018-02-28","cited_by_count":219},{"id":"2102.11107","title":"Towards Causal Representation Learning","created":"2021-02-22","cited_by_count":209},{"id":"1810.08678","title":"Optimization of Molecules via Deep Reinforcement Learning","created":"2018-10-19","cited_by_count":200},{"id":"1908.08342","title":"A Generalized Algorithm for Multi-Objective Reinforcement Learning and Policy Adaptation","created":"2019-08-21","cited_by_count":177},{"id":"1802.10567","title":"Learning by Playing - Solving Sparse Reward Tasks from Scratch","created":"2018-02-28","cited_by_count":167},{"id":"1510.09142","title":"Learning Continuous Control Policies by Stochastic Value Gradients","created":"2015-10-30","cited_by_count":162},{"id":"1711.10907","title":"Deep Reinforcement Learning for De-Novo Drug Design","created":"2017-11-29","cited_by_count":161},{"id":"1705.10843","title":"Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models","created":"2017-05-30","cited_by_count":117},{"id":"1905.11600","title":"GraphNVP: An Invertible Flow Model for Generating Molecular Graphs","created":"2019-05-28","cited_by_count":116},{"id":"2107.06277","title":"Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability","created":"2021-07-13","cited_by_count":109},{"id":"1911.02140","title":"Fully Parameterized Quantile Function for Distributional Reinforcement Learning","created":"2019-11-05","cited_by_count":88},{"id":"1905.13372","title":"MolecularRNN: Generating realistic molecular graphs with optimized properties","created":"2019-05-31","cited_by_count":82},{"id":"1806.05805","title":"Molecular generative model based on conditional variational autoencoder for de novo molecular design","created":"2018-06-15","cited_by_count":73},{"id":"1705.08417","title":"Reinforcement Learning with a Corrupted Reward Channel","created":"2017-05-23","cited_by_count":70},{"id":"2004.12485","title":"Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning","created":"2020-04-26","cited_by_count":57},{"id":"1902.01240","title":"PIPPS: Flexible Model-Based Policy Search Robust to the Curse of Chaos","created":"2019-02-04","cited_by_count":56},{"id":"2011.12747","title":"Symmetry-Aware Actor-Critic for 3D Molecular Design","created":"2020-11-25","cited_by_count":55},{"id":"2002.07717","title":"Reinforcement Learning for Molecular Design Guided by Quantum Mechanics","created":"2020-02-18","cited_by_count":51},{"id":"2007.04897","title":"Guiding Deep Molecular Optimization with Genetic Exploration","created":"2020-07-04","cited_by_count":51},{"id":"1805.00108","title":"Conditional molecular design with deep generative models","created":"2018-04-30","cited_by_count":44},{"id":"1902.07198","title":"Learning to Generalize from Sparse and Underspecified Rewards","created":"2019-02-19","cited_by_count":39},{"id":"2005.08158","title":"Optimizing for the Future in Non-Stationary MDPs","created":"2020-05-17","cited_by_count":37},{"id":"2004.14308","title":"Molecular Design in Synthetically Accessible Chemical Space via Deep Reinforcement Learning","created":"2020-04-29","cited_by_count":32},{"id":"2110.04422","title":"Theoretically Principled Deep RL Acceleration via Nearest Neighbor Function Approximation","created":"2021-10-09","cited_by_count":11},{"id":"2106.06932","title":"Characterizing the Gap Between Actor-Critic and Policy Gradient","created":"2021-06-13","cited_by_count":9},{"id":"1311.5918","title":"Empirical Dynamic Programming","created":"2013-11-22","cited_by_count":6},{"id":"2111.14283","title":"Exploration of Dark Chemical Genomics Space via Portal Learning: Applied to Targeting the Undruggable Genome and COVID-19 Anti-Infective Polypharmacology","created":"2021-11-23","cited_by_count":1}],"next_cursor":null}