{"list":"other","total":53,"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":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"1601.00670","title":"Variational Inference: A Review for Statisticians","created":"2016-01-04","cited_by_count":1472},{"id":"1611.00712","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","created":"2016-11-02","cited_by_count":1148},{"id":"2009.00236","title":"A Survey of Deep Active Learning","created":"2020-08-30","cited_by_count":554},{"id":"1802.05438","title":"Mean Field Multi-Agent Reinforcement Learning","created":"2018-02-15","cited_by_count":207},{"id":"2103.04931","title":"Monte Carlo Tree Search: A Review of Recent Modifications and Applications","created":"2021-03-08","cited_by_count":161},{"id":"1602.04450","title":"Bayesian Optimization with Safety Constraints: Safe and Automatic Parameter Tuning in Robotics","created":"2016-02-14","cited_by_count":134},{"id":"2105.08140","title":"Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning","created":"2021-05-17","cited_by_count":126},{"id":"2006.07169","title":"Shared Experience Actor-Critic for Multi-Agent Reinforcement Learning","created":"2020-06-12","cited_by_count":116},{"id":"2001.08726","title":"Interpretable End-to-end Urban Autonomous Driving with Latent Deep Reinforcement Learning","created":"2020-01-23","cited_by_count":103},{"id":"2102.07475","title":"Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing","created":"2021-02-15","cited_by_count":87},{"id":"1909.09884","title":"Uncertainty Quantification with Statistical Guarantees in End-to-End Autonomous Driving Control","created":"2019-09-21","cited_by_count":61},{"id":"2201.09802","title":"Constrained Policy Optimization via Bayesian World Models","created":"2022-01-24","cited_by_count":57},{"id":"1304.5350","title":"Parallel Gaussian Process Optimization with Upper Confidence Bound and Pure Exploration","created":"2013-04-19","cited_by_count":50},{"id":"1807.08912","title":"Meta-Learning Priors for Efficient Online Bayesian Regression","created":"2018-07-24","cited_by_count":48},{"id":"2003.02471","title":"Data-efficient Domain Randomization with Bayesian Optimization","created":"2020-03-05","cited_by_count":47},{"id":"2102.05762","title":"Risk-Averse Bayes-Adaptive Reinforcement Learning","created":"2021-02-10","cited_by_count":29},{"id":"1909.04121","title":"AC-Teach: A Bayesian Actor-Critic Method for Policy Learning with an Ensemble of Suboptimal Teachers","created":"2019-09-09","cited_by_count":28},{"id":"2105.13281","title":"GoSafe: Globally Optimal Safe Robot Learning","created":"2021-05-27","cited_by_count":27},{"id":"2003.00370","title":"PlaNet of the Bayesians: Reconsidering and Improving Deep Planning Network by Incorporating Bayesian Inference","created":"2020-03-01","cited_by_count":23},{"id":"2006.11441","title":"Task-Agnostic Online Reinforcement Learning with an Infinite Mixture of Gaussian Processes","created":"2020-06-19","cited_by_count":23},{"id":"2007.14196","title":"Lifelong Incremental Reinforcement Learning with Online Bayesian Inference","created":"2020-07-28","cited_by_count":23},{"id":"2104.07495","title":"Curiosity-Driven Exploration via Latent Bayesian Surprise","created":"2021-04-15","cited_by_count":22},{"id":"2104.00078","title":"Learning Human Objectives from Sequences of Physical Corrections","created":"2021-03-31","cited_by_count":21},{"id":"2109.14700","title":"Safety Assurances for Human-Robot Interaction via Confidence-aware Game-theoretic Human Models","created":"2021-09-29","cited_by_count":21},{"id":"1906.11021","title":"Cooperation-Aware Reinforcement Learning for Merging in Dense Traffic","created":"2019-06-26","cited_by_count":20},{"id":"2107.09822","title":"Bayesian Controller Fusion: Leveraging Control Priors in Deep Reinforcement Learning for Robotics","created":"2021-07-21","cited_by_count":20},{"id":"1903.02504","title":"Spiking Neural Network on Neuromorphic Hardware for Energy-Efficient Unidimensional SLAM","created":"2019-03-06","cited_by_count":19},{"id":"1909.09593","title":"Bayesian Optimization for Iterative Learning","created":"2019-09-20","cited_by_count":19},{"id":"1910.02325","title":"Bayesian Learning-Based Adaptive Control for Safety Critical Systems","created":"2019-10-05","cited_by_count":19},{"id":"2306.01122","title":"On the Convergence of Coordinate Ascent Variational Inference","created":"2023-06-01","cited_by_count":18},{"id":"1711.10453","title":"Deep Predictive Models for Collision Risk Assessment in Autonomous Driving","created":"2017-11-28","cited_by_count":15},{"id":"1404.1140","title":"Scalable Planning and Learning for Multiagent POMDPs: Extended Version","created":"2014-04-04","cited_by_count":14},{"id":"2007.13151","title":"Modeling and Predicting Trust Dynamics in Human-Robot Teaming: A Bayesian Inference Approach","created":"2020-07-26","cited_by_count":14},{"id":"2111.03165","title":"Infinite Time Horizon Safety of Bayesian Neural Networks","created":"2021-11-04","cited_by_count":13},{"id":"1812.04128","title":"Probabilistic Model Checking of Robots Deployed in Extreme Environments","created":"2018-12-10","cited_by_count":12},{"id":"2011.09445","title":"Cautious Bayesian Optimization for Efficient and Scalable Policy Search","created":"2020-11-18","cited_by_count":12},{"id":"2004.14594","title":"$\\mathcal{L}_1$-$\\mathcal{GP}$: $\\mathcal{L}_1$ Adaptive Control with Bayesian Learning","created":"2020-04-30","cited_by_count":11},{"id":"1802.01780","title":"Goal Inference Improves Objective and Perceived Performance in Human-Robot Collaboration","created":"2018-02-06","cited_by_count":10},{"id":"2011.08985","title":"A User's Guide to Calibrating Robotics Simulators","created":"2020-11-17","cited_by_count":10},{"id":"2011.06118","title":"I Know What You Meant: Learning Human Objectives by (Under)estimating Their Choice Set","created":"2020-11-11","cited_by_count":9},{"id":"1412.0630","title":"Batch Nonlinear Continuous-Time Trajectory Estimation as Exactly Sparse Gaussian Process Regression","created":"2014-12-01","cited_by_count":8},{"id":"2002.04794","title":"Computing the racing line using Bayesian optimization","created":"2020-02-12","cited_by_count":8},{"id":"1911.08701","title":"Bayesian Curiosity for Efficient Exploration in Reinforcement Learning","created":"2019-11-20","cited_by_count":7},{"id":"2004.00662","title":"Bayesian Safe Learning and Control with Sum-of-Squares Analysis and Polynomial Kernels","created":"2020-04-01","cited_by_count":7},{"id":"2108.00276","title":"Risk Averse Bayesian Reward Learning for Autonomous Navigation from Human Demonstration","created":"2021-07-31","cited_by_count":4},{"id":"1911.03308","title":"Fully Bayesian Recurrent Neural Networks for Safe Reinforcement Learning","created":"2019-11-08","cited_by_count":3},{"id":"2104.03807","title":"A Bayesian Approach to Reinforcement Learning of Vision-Based Vehicular Control","created":"2021-04-08","cited_by_count":3},{"id":"2301.12776","title":"PAC-Bayesian Soft Actor-Critic Learning","created":"2023-01-30","cited_by_count":3},{"id":"1911.07712","title":"Inducing Cooperation via Team Regret Minimization based Multi-Agent Deep Reinforcement Learning","created":"2019-11-18","cited_by_count":2},{"id":"2303.11047","title":"Practical Realization of Bessel's Correction for a Bias-Free Estimation of the Auto-Covariance and the Cross-Covariance Functions","created":"2023-03-20","cited_by_count":2}],"next_cursor":null}