{"list":"other","total":79,"rows":[{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"1803.10122","title":"World Models","created":"2018-03-27","cited_by_count":1513},{"id":"1606.04671","title":"Progressive Neural Networks","created":"2016-06-15","cited_by_count":1361},{"id":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"id":"1906.02691","title":"An Introduction to Variational Autoencoders","created":"2019-06-06","cited_by_count":1000},{"id":"2011.06225","title":"A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges","created":"2020-11-12","cited_by_count":819},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807},{"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":"2107.03342","title":"A Survey of Uncertainty in Deep Neural Networks","created":"2021-07-07","cited_by_count":680},{"id":"1902.02476","title":"A Simple Baseline for Bayesian Uncertainty in Deep Learning","created":"2019-02-07","cited_by_count":560},{"id":"1907.05388","title":"Provably Efficient Reinforcement Learning with Linear Function Approximation","created":"2019-07-11","cited_by_count":520},{"id":"1606.05312","title":"Successor Features for Transfer in Reinforcement Learning","created":"2016-06-16","cited_by_count":340},{"id":"1808.04355","title":"Large-Scale Study of Curiosity-Driven Learning","created":"2018-08-13","cited_by_count":280},{"id":"2004.12919","title":"First return, then explore","created":"2020-04-27","cited_by_count":266},{"id":"2009.07888","title":"Transfer Learning in Deep Reinforcement Learning: A Survey","created":"2020-09-16","cited_by_count":265},{"id":"1703.01310","title":"Count-Based Exploration with Neural Density Models","created":"2017-03-03","cited_by_count":257},{"id":"2006.01107","title":"Model-Based Reinforcement Learning with Value-Targeted Regression","created":"2020-06-01","cited_by_count":234},{"id":"1806.03335","title":"Randomized Prior Functions for Deep Reinforcement Learning","created":"2018-06-08","cited_by_count":219},{"id":"1905.10389","title":"Reinforcement Learning in Feature Space: Matrix Bandit, Kernels, and Regret Bound","created":"2019-05-24","cited_by_count":201},{"id":"2003.00153","title":"Learning Near Optimal Policies with Low Inherent Bellman Error","created":"2020-02-29","cited_by_count":181},{"id":"1807.01675","title":"Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion","created":"2018-07-04","cited_by_count":168},{"id":"1906.05030","title":"Fast Task Inference with Variational Intrinsic Successor Features","created":"2019-06-12","cited_by_count":133},{"id":"2101.05265","title":"Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning","created":"2021-01-13","cited_by_count":123},{"id":"1406.1853","title":"Model-based Reinforcement Learning and the Eluder Dimension","created":"2014-06-07","cited_by_count":116},{"id":"2103.07945","title":"Learning One Representation to Optimize All Rewards","created":"2021-03-14","cited_by_count":115},{"id":"1807.11622","title":"Count-Based Exploration with the Successor Representation","created":"2018-07-31","cited_by_count":112},{"id":"1809.05214","title":"Model-Based Reinforcement Learning via Meta-Policy Optimization","created":"2018-09-14","cited_by_count":101},{"id":"1502.02860","title":"Gaussian Processes for Data-Efficient Learning in Robotics and Control","created":"2015-02-10","cited_by_count":98},{"id":"2006.13916","title":"Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers","created":"2020-06-24","cited_by_count":97},{"id":"2007.07461","title":"Model-Based Multi-Agent RL in Zero-Sum Markov Games with Near-Optimal Sample Complexity","created":"2020-07-15","cited_by_count":92},{"id":"2007.13442","title":"Fast active learning for pure exploration in reinforcement learning","created":"2020-07-27","cited_by_count":92},{"id":"1901.10964","title":"Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Improvement","created":"2019-01-30","cited_by_count":88},{"id":"1810.04586","title":"The Laplacian in RL: Learning Representations with Efficient Approximations","created":"2018-10-10","cited_by_count":86},{"id":"1606.02396","title":"Deep Successor Reinforcement Learning","created":"2016-06-08","cited_by_count":72},{"id":"1905.09638","title":"Estimating Risk and Uncertainty in Deep Reinforcement Learning","created":"2019-05-23","cited_by_count":70},{"id":"1705.10257","title":"Boltzmann Exploration Done Right","created":"2017-05-29","cited_by_count":69},{"id":"1802.04412","title":"Efficient Exploration through Bayesian Deep Q-Networks","created":"2018-02-13","cited_by_count":67},{"id":"2106.13105","title":"The Option Keyboard: Combining Skills in Reinforcement Learning","created":"2021-06-24","cited_by_count":67},{"id":"1905.06125","title":"Distributional Reinforcement Learning for Efficient Exploration","created":"2019-05-13","cited_by_count":60},{"id":"1612.05533","title":"Deep Reinforcement Learning with Successor Features for Navigation across Similar Environments","created":"2016-12-16","cited_by_count":50},{"id":"2105.02796","title":"Practical and Rigorous Uncertainty Bounds for Gaussian Process Regression","created":"2021-05-06","cited_by_count":49},{"id":"2107.02729","title":"AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning","created":"2021-07-06","cited_by_count":48},{"id":"1812.02464","title":"Pseudo-Rehearsal: Achieving Deep Reinforcement Learning without Catastrophic Forgetting","created":"2018-12-06","cited_by_count":46},{"id":"2010.00581","title":"Emergent Social Learning via Multi-agent Reinforcement Learning","created":"2020-10-01","cited_by_count":44},{"id":"2208.09052","title":"A Review of Uncertainty for Deep Reinforcement Learning","created":"2022-08-18","cited_by_count":40},{"id":"2205.14571","title":"Provable Benefits of Representational Transfer in Reinforcement Learning","created":"2022-05-29","cited_by_count":38},{"id":"1810.06530","title":"Successor Uncertainties: Exploration and Uncertainty in Temporal Difference Learning","created":"2018-10-15","cited_by_count":35},{"id":"2106.08053","title":"On the Power of Multitask Representation Learning in Linear MDP","created":"2021-06-15","cited_by_count":30},{"id":"1907.08956","title":"Tutorial: Deriving the Standard Variational Autoencoder (VAE) Loss Function","created":"2019-07-21","cited_by_count":26},{"id":"2102.12560","title":"PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning","created":"2021-02-24","cited_by_count":23},{"id":"2206.11326","title":"Optimistic Linear Support and Successor Features as a Basis for Optimal Policy Transfer","created":"2022-06-22","cited_by_count":22},{"id":"2001.04025","title":"Universal Successor Features for Transfer Reinforcement Learning","created":"2020-01-05","cited_by_count":20},{"id":"2011.11827","title":"REPAINT: Knowledge Transfer in Deep Reinforcement Learning","created":"2020-11-24","cited_by_count":14},{"id":"1912.05328","title":"Efficient and Robust Reinforcement Learning with Uncertainty-based Value Expansion","created":"2019-12-10","cited_by_count":13},{"id":"1906.09480","title":"A neurally plausible model learns successor representations in partially observable environments","created":"2019-06-22","cited_by_count":12},{"id":"1907.04964","title":"A Model-based Approach for Sample-efficient Multi-task Reinforcement Learning","created":"2019-07-11","cited_by_count":12},{"id":"1911.11397","title":"Adaptive dynamic programming for nonaffine nonlinear optimal control problem with state constraints","created":"2019-11-26","cited_by_count":12},{"id":"2103.02886","title":"Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddings","created":"2021-03-04","cited_by_count":12},{"id":"2105.14127","title":"Risk-Aware Transfer in Reinforcement Learning using Successor Features","created":"2021-05-28","cited_by_count":12},{"id":"1905.02636","title":"A Complementary Learning Systems Approach to Temporal Difference Learning","created":"2019-05-07","cited_by_count":11},{"id":"1911.12574","title":"Deep Model-Based Reinforcement Learning via Estimated Uncertainty and Conservative Policy Optimization","created":"2019-11-28","cited_by_count":11},{"id":"1804.03758","title":"Universal Successor Representations for Transfer Reinforcement Learning","created":"2018-04-11","cited_by_count":10},{"id":"2107.06466","title":"Going Beyond Linear RL: Sample Efficient Neural Function Approximation","created":"2021-07-14","cited_by_count":9},{"id":"2002.07171","title":"Kalman meets Bellman: Improving Policy Evaluation through Value Tracking","created":"2020-02-17","cited_by_count":7},{"id":"1809.08923","title":"Target Transfer Q-Learning and Its Convergence Analysis","created":"2018-09-21","cited_by_count":6},{"id":"2006.00195","title":"MM-KTD: Multiple Model Kalman Temporal Differences for Reinforcement Learning","created":"2020-05-30","cited_by_count":6},{"id":"2103.02650","title":"Successor Feature Sets: Generalizing Successor Representations Across Policies","created":"2021-03-03","cited_by_count":6},{"id":"2108.06526","title":"Fractional Transfer Learning for Deep Model-Based Reinforcement Learning","created":"2021-08-14","cited_by_count":6},{"id":"1811.07350","title":"Policy Optimization with Model-based Explorations","created":"2018-11-18","cited_by_count":5},{"id":"1906.10717","title":"Uncertainty-aware Model-based Policy Optimization","created":"2019-06-25","cited_by_count":5},{"id":"1910.02532","title":"Probabilistic Successor Representations with Kalman Temporal Differences","created":"2019-10-06","cited_by_count":5},{"id":"1908.06376","title":"VUSFA:Variational Universal Successor Features Approximator to Improve Transfer DRL for Target Driven Visual Navigation","created":"2019-08-18","cited_by_count":4},{"id":"2002.10021","title":"How Transferable are the Representations Learned by Deep Q Agents?","created":"2020-02-24","cited_by_count":4},{"id":"2103.02225","title":"Foresee then Evaluate: Decomposing Value Estimation with Latent Future Prediction","created":"2021-03-03","cited_by_count":3},{"id":"2110.02639","title":"On The Transferability of Deep-Q Networks","created":"2021-10-06","cited_by_count":3},{"id":"2210.06168","title":"The Role of Exploration for Task Transfer in Reinforcement Learning","created":"2022-10-11","cited_by_count":2},{"id":"2006.11975","title":"Toward the biological model of the hippocampus as the successor representation agent","created":"2020-06-22","cited_by_count":1},{"id":"2204.00049","title":"AKF-SR: Adaptive Kalman Filtering-based Successor Representation","created":"2022-03-31","cited_by_count":1}],"next_cursor":null}