{"list":"other","total":107,"rows":[{"id":"2004.13649","title":"Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels","created":"2020-04-28","cited_by_count":585},{"id":"2006.10742","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","created":"2020-06-18","cited_by_count":436},{"id":"2007.03964","title":"Responsive Safety in Reinforcement Learning by PID Lagrangian Methods","created":"2020-07-08","cited_by_count":316},{"id":"1910.01741","title":"Improving Sample Efficiency in Model-Free Reinforcement Learning from Images","created":"2019-10-02","cited_by_count":274},{"id":"2003.08938","title":"Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations","created":"2020-03-19","cited_by_count":238},{"id":"1910.12809","title":"Minimax Weight and Q-Function Learning for Off-Policy Evaluation","created":"2019-10-28","cited_by_count":150},{"id":"1908.08526","title":"Double Reinforcement Learning for Efficient Off-Policy Evaluation in Markov Decision Processes","created":"2019-08-22","cited_by_count":119},{"id":"1906.03173","title":"Ego-Pose Estimation and Forecasting as Real-Time PD Control","created":"2019-06-07","cited_by_count":87},{"id":"1810.01032","title":"Reinforcement Learning with Perturbed Rewards","created":"2018-10-02","cited_by_count":79},{"id":"1906.07516","title":"Robust Reinforcement Learning for Continuous Control with Model Misspecification","created":"2019-06-18","cited_by_count":78},{"id":"2008.01976","title":"Robust Deep Reinforcement Learning through Adversarial Loss","created":"2020-08-05","cited_by_count":75},{"id":"1707.07402","title":"Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback","created":"2017-07-24","cited_by_count":72},{"id":"1810.08700","title":"Safe Reinforcement Learning with Model Uncertainty Estimates","created":"2018-10-19","cited_by_count":72},{"id":"1909.11639","title":"ROBEL: Robotics Benchmarks for Learning with Low-Cost Robots","created":"2019-09-25","cited_by_count":72},{"id":"1911.08689","title":"Corruption-robust exploration in episodic reinforcement learning","created":"2019-11-20","cited_by_count":72},{"id":"2006.12862","title":"Automatic Data Augmentation for Generalization in Deep Reinforcement Learning","created":"2020-06-23","cited_by_count":71},{"id":"2008.01825","title":"Robust Reinforcement Learning using Adversarial Populations","created":"2020-08-04","cited_by_count":66},{"id":"2009.08311","title":"Multimodal Safety-Critical Scenarios Generation for Decision-Making Algorithms Evaluation","created":"2020-09-16","cited_by_count":55},{"id":"2005.04323","title":"ALLSTEPS: Curriculum-driven Learning of Stepping Stone Skills","created":"2020-05-09","cited_by_count":54},{"id":"1906.05862","title":"Sub-policy Adaptation for Hierarchical Reinforcement Learning","created":"2019-06-13","cited_by_count":47},{"id":"1910.12908","title":"Certified Adversarial Robustness for Deep Reinforcement Learning","created":"2019-10-28","cited_by_count":47},{"id":"1910.09496","title":"Policy Optimization for $\\mathcal{H}_2$ Linear Control with $\\mathcal{H}_\\infty$ Robustness Guarantee: Implicit Regularization and Global Convergence","created":"2019-10-21","cited_by_count":46},{"id":"2002.06063","title":"Robust Reinforcement Learning via Adversarial training with Langevin Dynamics","created":"2020-02-14","cited_by_count":45},{"id":"2004.14288","title":"Actor-Critic Reinforcement Learning for Control with Stability Guarantee","created":"2020-04-29","cited_by_count":45},{"id":"2106.04493","title":"A Deep Value-network Based Approach for Multi-Driver Order Dispatching","created":"2021-06-08","cited_by_count":45},{"id":"2008.05533","title":"Overcoming Model Bias for Robust Offline Deep Reinforcement Learning","created":"2020-08-12","cited_by_count":43},{"id":"2003.12151","title":"Q-Learning in Regularized Mean-field Games","created":"2020-03-24","cited_by_count":42},{"id":"2003.02894","title":"Distributional Robustness and Regularization in Reinforcement Learning","created":"2020-03-05","cited_by_count":40},{"id":"2003.03722","title":"On the Robustness of Cooperative Multi-Agent Reinforcement Learning","created":"2020-03-08","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":"2006.10412","title":"Towards Open Ad Hoc Teamwork Using Graph-based Policy Learning","created":"2020-06-18","cited_by_count":37},{"id":"1902.09458","title":"Long-Range Indoor Navigation with PRM-RL","created":"2019-02-25","cited_by_count":31},{"id":"2007.07176","title":"Robustifying Reinforcement Learning Agents via Action Space Adversarial Training","created":"2020-07-14","cited_by_count":30},{"id":"2005.00585","title":"Improving Robustness via Risk Averse Distributional Reinforcement Learning","created":"2020-05-01","cited_by_count":28},{"id":"2006.04363","title":"Mitigating Value Hallucination in Dyna Planning via Multistep Predecessor Models","created":"2020-06-08","cited_by_count":28},{"id":"2009.14711","title":"S3K: Self-Supervised Semantic Keypoints for Robotic Manipulation via Multi-View Consistency","created":"2020-09-30","cited_by_count":28},{"id":"1908.01887","title":"DoorGym: A Scalable Door Opening Environment And Baseline Agent","created":"2019-08-05","cited_by_count":26},{"id":"2006.14156","title":"Multi-Agent Deep Reinforcement Learning for HVAC Control in Commercial Buildings","created":"2020-06-25","cited_by_count":26},{"id":"1712.07893","title":"A Deep Policy Inference Q-Network for Multi-Agent Systems","created":"2017-12-21","cited_by_count":25},{"id":"2002.04014","title":"Statistically Efficient Off-Policy Policy Gradients","created":"2020-02-10","cited_by_count":25},{"id":"2003.06069","title":"A General Framework for Learning Mean-Field Games","created":"2020-03-13","cited_by_count":25},{"id":"2002.12078","title":"Training Adversarial Agents to Exploit Weaknesses in Deep Control Policies","created":"2020-02-27","cited_by_count":24},{"id":"1909.12397","title":"CAQL: Continuous Action Q-Learning","created":"2019-09-26","cited_by_count":23},{"id":"2006.00945","title":"Robust Reinforcement Learning with Wasserstein Constraint","created":"2020-06-01","cited_by_count":21},{"id":"1603.09173","title":"Riemannian game dynamics","created":"2016-03-30","cited_by_count":19},{"id":"2006.06069","title":"Robust Spammer Detection by Nash Reinforcement Learning","created":"2020-06-10","cited_by_count":17},{"id":"2006.12841","title":"Online Multi-agent Reinforcement Learning for Decentralized Inverter-based Volt-VAR Control","created":"2020-06-23","cited_by_count":17},{"id":"2008.10861","title":"t-Soft Update of Target Network for Deep Reinforcement Learning","created":"2020-08-25","cited_by_count":17},{"id":"1906.04585","title":"Gossip-based Actor-Learner Architectures for Deep Reinforcement Learning","created":"2019-06-09","cited_by_count":16},{"id":"1907.07500","title":"Learning Variable Impedance Control for Contact Sensitive Tasks","created":"2019-07-17","cited_by_count":16},{"id":"1910.13399","title":"Robust Model-free Reinforcement Learning with Multi-objective Bayesian Optimization","created":"2019-10-29","cited_by_count":16},{"id":"2006.13173","title":"Deep Reinforcement Learning Control for Radar Detection and Tracking in Congested Spectral Environments","created":"2020-06-23","cited_by_count":15},{"id":"2008.02430","title":"Contrastive Variational Reinforcement Learning for Complex Observations","created":"2020-08-06","cited_by_count":15},{"id":"2002.01068","title":"Policy Gradient based Quantum Approximate Optimization Algorithm","created":"2020-02-04","cited_by_count":14},{"id":"1910.05405","title":"Zap Q-Learning With Nonlinear Function Approximation","created":"2019-10-11","cited_by_count":13},{"id":"1910.10537","title":"Robust Visual Domain Randomization for Reinforcement Learning","created":"2019-10-23","cited_by_count":13},{"id":"2002.01428","title":"Learning Task-Driven Control Policies via Information Bottlenecks","created":"2020-02-04","cited_by_count":13},{"id":"2002.09027","title":"Enhanced Adversarial Strategically-Timed Attacks against Deep Reinforcement Learning","created":"2020-02-20","cited_by_count":13},{"id":"2009.11212","title":"Robust Reinforcement Learning-based Autonomous Driving Agent for Simulation and Real World","created":"2020-09-23","cited_by_count":12},{"id":"1909.08735","title":"Robust Opponent Modeling via Adversarial Ensemble Reinforcement Learning in Asymmetric Imperfect-Information Games","created":"2019-09-18","cited_by_count":11},{"id":"2004.12399","title":"Reinforcement Learning Generalization with Surprise Minimization","created":"2020-04-26","cited_by_count":10},{"id":"2007.09380","title":"CATCH: Context-based Meta Reinforcement Learning for Transferrable Architecture Search","created":"2020-07-18","cited_by_count":10},{"id":"1912.08324","title":"Analysing Deep Reinforcement Learning Agents Trained with Domain Randomisation","created":"2019-12-18","cited_by_count":9},{"id":"2002.08537","title":"Adaptive Temporal Difference Learning with Linear Function Approximation","created":"2020-02-20","cited_by_count":9},{"id":"2008.04388","title":"GRIMGEP: Learning Progress for Robust Goal Sampling in Visual Deep Reinforcement Learning","created":"2020-08-10","cited_by_count":9},{"id":"2006.03886","title":"Efficient Evaluation of Natural Stochastic Policies in Offline Reinforcement Learning","created":"2020-06-06","cited_by_count":8},{"id":"1808.07982","title":"Proximal Policy Optimization and its Dynamic Version for Sequence Generation","created":"2018-08-24","cited_by_count":7},{"id":"1910.02789","title":"Language is Power: Representing States Using Natural Language in Reinforcement Learning","created":"2019-10-02","cited_by_count":7},{"id":"1911.02875","title":"$H_\\infty$ Model-free Reinforcement Learning with Robust Stability Guarantee","created":"2019-11-07","cited_by_count":7},{"id":"2003.04069","title":"Zooming for Efficient Model-Free Reinforcement Learning in Metric Spaces","created":"2020-03-09","cited_by_count":7},{"id":"2004.10886","title":"Stability-Guaranteed Reinforcement Learning for Contact-rich Manipulation","created":"2020-04-22","cited_by_count":7},{"id":"2005.08114","title":"Mutual Information Maximization for Robust Plannable Representations","created":"2020-05-16","cited_by_count":7},{"id":"2006.05554","title":"Causal Discovery from Incomplete Data using An Encoder and Reinforcement Learning","created":"2020-06-09","cited_by_count":7},{"id":"2006.11764","title":"Gradient-EM Bayesian Meta-learning","created":"2020-06-21","cited_by_count":7},{"id":"2008.11592","title":"Robust Reinforcement Learning: A Case Study in Linear Quadratic Regulation","created":"2020-08-25","cited_by_count":7},{"id":"1802.02274","title":"A Critical Investigation of Deep Reinforcement Learning for Navigation","created":"2018-02-07","cited_by_count":6},{"id":"1905.13547","title":"Learning robust control for LQR systems with multiplicative noise via policy gradient","created":"2019-05-28","cited_by_count":6},{"id":"1910.05766","title":"QoS and Jamming-Aware Wireless Networking Using Deep Reinforcement Learning","created":"2019-10-13","cited_by_count":6},{"id":"2004.04292","title":"Adaptive Stress Testing without Domain Heuristics using Go-Explore","created":"2020-04-08","cited_by_count":6},{"id":"2007.00691","title":"Falsification-Based Robust Adversarial Reinforcement Learning","created":"2020-07-01","cited_by_count":6},{"id":"2008.07875","title":"Towards Closing the Sim-to-Real Gap in Collaborative Multi-Robot Deep Reinforcement Learning","created":"2020-08-18","cited_by_count":6},{"id":"2009.14280","title":"Learning to swim in potential flow","created":"2020-09-30","cited_by_count":6},{"id":"2008.08157","title":"Heteroscedastic Uncertainty for Robust Generative Latent Dynamics","created":"2020-08-18","cited_by_count":5},{"id":"2002.03042","title":"Bayesian Residual Policy Optimization: Scalable Bayesian Reinforcement Learning with Clairvoyant Experts","created":"2020-02-07","cited_by_count":4},{"id":"2005.08006","title":"Lifelong Control of Off-grid Microgrid with Model Based Reinforcement Learning","created":"2020-05-16","cited_by_count":4},{"id":"2005.09476","title":"Learning to Herd Agents Amongst Obstacles: Training Robust Shepherding Behaviors using Deep Reinforcement Learning","created":"2020-05-19","cited_by_count":4},{"id":"2006.11608","title":"Robust Reinforcement Learning using Least Squares Policy Iteration with Provable Performance Guarantees","created":"2020-06-20","cited_by_count":4},{"id":"2006.16498","title":"Accelerating Reinforcement Learning Agent with EEG-based Implicit Human Feedback","created":"2020-06-30","cited_by_count":4},{"id":"2008.06199","title":"Adversary Agnostic Robust Deep Reinforcement Learning","created":"2020-08-14","cited_by_count":4},{"id":"2001.06808","title":"Discriminator Soft Actor Critic without Extrinsic Rewards","created":"2020-01-19","cited_by_count":3},{"id":"2003.00667","title":"MVP: Unified Motion and Visual Self-Supervised Learning for Large-Scale Robotic Navigation","created":"2020-03-02","cited_by_count":3},{"id":"2003.03758","title":"Reinforcement Learning Based Cooperative Coded Caching under Dynamic Popularities in Ultra-Dense Networks","created":"2020-03-08","cited_by_count":3},{"id":"2003.10903","title":"Distributional Reinforcement Learning with Ensembles","created":"2020-03-24","cited_by_count":3},{"id":"2006.07808","title":"Reinforcement Learning with Supervision from Noisy Demonstrations","created":"2020-06-14","cited_by_count":3},{"id":"2008.04403","title":"Comparison of Model Predictive and Reinforcement Learning Methods for Fault Tolerant Control","created":"2020-08-10","cited_by_count":3},{"id":"1903.12311","title":"Mesh-based Tools to Analyze Deep Reinforcement Learning Policies for Underactuated Biped Locomotion","created":"2019-03-29","cited_by_count":2},{"id":"2003.00179","title":"TAdam: A Robust Stochastic Gradient Optimizer","created":"2020-02-29","cited_by_count":2},{"id":"2006.10190","title":"Learning to Track Dynamic Targets in Partially Known Environments","created":"2020-06-17","cited_by_count":2},{"id":"2007.14983","title":"Adversarial Robustness for Machine Learning Cyber Defenses Using Log Data","created":"2020-07-29","cited_by_count":2},{"id":"2007.15242","title":"Understanding the Stability of Deep Control Policies for Biped Locomotion","created":"2020-07-30","cited_by_count":2}],"next_cursor":"100"}