{"list":"other","total":68,"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":"1606.03476","title":"Generative Adversarial Imitation Learning","created":"2016-06-10","cited_by_count":1597},{"id":"1702.08165","title":"Reinforcement Learning with Deep Energy-Based Policies","created":"2017-02-27","cited_by_count":669},{"id":"1710.11248","title":"Learning Robust Rewards with Adversarial Inverse Reinforcement Learning","created":"2017-10-30","cited_by_count":490},{"id":"1507.06527","title":"Deep Recurrent Q-Learning for Partially Observable MDPs","created":"2015-07-23","cited_by_count":465},{"id":"1811.06711","title":"An Algorithmic Perspective on Imitation Learning","created":"2018-11-16","cited_by_count":459},{"id":"1603.00448","title":"Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization","created":"2016-03-01","cited_by_count":406},{"id":"1904.06387","title":"Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations","created":"2019-04-12","cited_by_count":260},{"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":"1911.02256","title":"A Divergence Minimization Perspective on Imitation Learning Methods","created":"2019-11-06","cited_by_count":190},{"id":"1912.05032","title":"Imitation Learning via Off-Policy Distribution Matching","created":"2019-12-10","cited_by_count":183},{"id":"1805.08328","title":"Verifiable Reinforcement Learning via Policy Extraction","created":"2018-05-22","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":"1806.02426","title":"Deep Variational Reinforcement Learning for POMDPs","created":"2018-06-06","cited_by_count":125},{"id":"1905.12888","title":"Imitation Learning as $f$-Divergence Minimization","created":"2019-05-30","cited_by_count":123},{"id":"2006.04678","title":"Primal Wasserstein Imitation Learning","created":"2020-06-08","cited_by_count":121},{"id":"2002.04833","title":"Reward-rational (implicit) choice: A unifying formalism for reward learning","created":"2020-02-12","cited_by_count":120},{"id":"1402.0635","title":"Generalization and Exploration via Randomized Value Functions","created":"2014-02-04","cited_by_count":112},{"id":"2002.09089","title":"Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences","created":"2020-02-21","cited_by_count":73},{"id":"1705.10257","title":"Boltzmann Exploration Done Right","created":"2017-05-29","cited_by_count":69},{"id":"2006.07532","title":"Online Bayesian Goal Inference for Boundedly-Rational Planning Agents","created":"2020-06-13","cited_by_count":68},{"id":"2011.04709","title":"f-IRL: Inverse Reinforcement Learning via State Marginal Matching","created":"2020-11-09","cited_by_count":67},{"id":"2006.13900","title":"Quantifying Differences in Reward Functions","created":"2020-06-24","cited_by_count":63},{"id":"1906.08113","title":"Wasserstein Adversarial Imitation Learning","created":"2019-06-19","cited_by_count":60},{"id":"2006.14154","title":"Strictly Batch Imitation Learning by Energy-based Distribution Matching","created":"2020-06-25","cited_by_count":54},{"id":"1905.01240","title":"Information asymmetry in KL-regularized RL","created":"2019-05-03","cited_by_count":53},{"id":"1605.08478","title":"Model-Free Imitation Learning with Policy Optimization","created":"2016-05-26","cited_by_count":52},{"id":"1804.06309","title":"On Improving Deep Reinforcement Learning for POMDPs","created":"2018-04-17","cited_by_count":50},{"id":"1906.09624","title":"On the Feasibility of Learning, Rather than Assuming, Human Biases for Reward Inference","created":"2019-06-23","cited_by_count":49},{"id":"1912.10703","title":"Variational Recurrent Models for Solving Partially Observable Control Tasks","created":"2019-12-23","cited_by_count":47},{"id":"1712.05812","title":"Occam's razor is insufficient to infer the preferences of irrational agents","created":"2017-12-15","cited_by_count":45},{"id":"1805.08010","title":"Where Do You Think You're Going?: Inferring Beliefs about Dynamics from Behavior","created":"2018-05-21","cited_by_count":40},{"id":"2012.05862","title":"Understanding Learned Reward Functions","created":"2020-12-10","cited_by_count":37},{"id":"1809.06404","title":"Adversarial Imitation via Variational Inverse Reinforcement Learning","created":"2018-09-17","cited_by_count":36},{"id":"2001.04032","title":"POPCORN: Partially Observed Prediction COnstrained ReiNforcement Learning","created":"2020-01-13","cited_by_count":36},{"id":"1906.10437","title":"Learning Causal State Representations of Partially Observable Environments","created":"2019-06-25","cited_by_count":30},{"id":"1612.02179","title":"Model-based Adversarial Imitation Learning","created":"2016-12-07","cited_by_count":29},{"id":"1705.05427","title":"Repeated Inverse Reinforcement Learning","created":"2017-05-15","cited_by_count":29},{"id":"1912.04472","title":"Deep Bayesian Reward Learning from Preferences","created":"2019-12-10","cited_by_count":28},{"id":"1903.10077","title":"Truly Batch Apprenticeship Learning with Deep Successor Features","created":"2019-03-24","cited_by_count":27},{"id":"1910.01913","title":"If MaxEnt RL is the Answer, What is the Question?","created":"2019-10-04","cited_by_count":27},{"id":"1604.03912","title":"Inverse Reinforcement Learning with Simultaneous Estimation of Rewards and Dynamics","created":"2016-04-13","cited_by_count":24},{"id":"1611.01626","title":"Combining policy gradient and Q-learning","created":"2016-11-05","cited_by_count":24},{"id":"2006.13258","title":"Adversarial Soft Advantage Fitting: Imitation Learning without Policy Optimization","created":"2020-06-23","cited_by_count":22},{"id":"1512.06789","title":"Information-Theoretic Bounded Rationality","created":"2015-12-21","cited_by_count":21},{"id":"1909.03198","title":"Soft Policy Gradient Method for Maximum Entropy Deep Reinforcement Learning","created":"2019-09-07","cited_by_count":20},{"id":"2010.01207","title":"$f$-GAIL: Learning $f$-Divergence for Generative Adversarial Imitation Learning","created":"2020-10-02","cited_by_count":20},{"id":"2011.05064","title":"What Did You Think Would Happen? Explaining Agent Behaviour Through Intended Outcomes","created":"2020-11-10","cited_by_count":20},{"id":"1601.06569","title":"Towards Resolving Unidentifiability in Inverse Reinforcement Learning","created":"2016-01-25","cited_by_count":18},{"id":"2008.03525","title":"Non-Adversarial Imitation Learning and its Connections to Adversarial Methods","created":"2020-08-08","cited_by_count":17},{"id":"1908.04696","title":"Inverse Rational Control with Partially Observable Continuous Nonlinear Dynamics","created":"2019-08-13","cited_by_count":16},{"id":"2011.08541","title":"Efficient Exploration of Reward Functions in Inverse Reinforcement Learning via Bayesian Optimization","created":"2020-11-17","cited_by_count":16},{"id":"1711.10055","title":"Risk-sensitive Inverse Reinforcement Learning via Semi- and Non-Parametric Methods","created":"2017-11-28","cited_by_count":12},{"id":"2006.14141","title":"Inverse Active Sensing: Modeling and Understanding Timely Decision-Making","created":"2020-06-25","cited_by_count":12},{"id":"1703.01585","title":"A Unified Bellman Equation for Causal Information and Value in Markov Decision Processes","created":"2017-03-05","cited_by_count":11},{"id":"1805.08336","title":"Maximum Causal Tsallis Entropy Imitation Learning","created":"2018-05-22","cited_by_count":10},{"id":"1604.02080","title":"Planning with Information-Processing Constraints and Model Uncertainty in Markov Decision Processes","created":"2016-04-07","cited_by_count":7},{"id":"2002.05769","title":"The Efficiency of Human Cognition Reflects Planned Information Processing","created":"2020-02-13","cited_by_count":6},{"id":"2006.11309","title":"Modelling Agent Policies with Interpretable Imitation Learning","created":"2020-06-19","cited_by_count":6},{"id":"1307.3785","title":"Probabilistic inverse reinforcement learning in unknown environments","created":"2013-07-14","cited_by_count":3},{"id":"1610.07505","title":"Balancing Suspense and Surprise: Timely Decision Making with Endogenous Information Acquisition","created":"2016-10-24","cited_by_count":3},{"id":"1708.01867","title":"An Information-Theoretic Optimality Principle for Deep Reinforcement Learning","created":"2017-08-06","cited_by_count":3},{"id":"1811.10746","title":"MATCH-Net: Dynamic Prediction in Survival Analysis using Convolutional Neural Networks","created":"2018-11-26","cited_by_count":3},{"id":"1606.01946","title":"Minimum-Information LQG Control - Part I: Memoryless Controllers","created":"2016-06-06","cited_by_count":2},{"id":"1606.01947","title":"Minimum-Information LQG Control - Part II: Retentive Controllers","created":"2016-06-06","cited_by_count":2},{"id":"1911.06928","title":"Generalized Maximum Causal Entropy for Inverse Reinforcement Learning","created":"2019-11-16","cited_by_count":2},{"id":"1805.09864","title":"Inverse Rational Control: Inferring What You Think from How You Forage","created":"2018-05-24","cited_by_count":1}],"next_cursor":null}