{"list":"other","total":137,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"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":"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":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"1606.03476","title":"Generative Adversarial Imitation Learning","created":"2016-06-10","cited_by_count":1597},{"id":"1911.08265","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","created":"2019-11-19","cited_by_count":1353},{"id":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"1705.10528","title":"Constrained Policy Optimization","created":"2017-05-30","cited_by_count":983},{"id":"1504.00702","title":"End-to-End Training of Deep Visuomotor Policies","created":"2015-04-02","cited_by_count":875},{"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":"1712.01815","title":"Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm","created":"2017-12-05","cited_by_count":734},{"id":"1811.06128","title":"Machine Learning for Combinatorial Optimization: a Methodological Tour d'Horizon","created":"2018-11-15","cited_by_count":623},{"id":"1710.11248","title":"Learning Robust Rewards with Adversarial Inverse Reinforcement Learning","created":"2017-10-30","cited_by_count":490},{"id":"2108.06266","title":"Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning","created":"2021-08-13","cited_by_count":371},{"id":"1806.06920","title":"Maximum a Posteriori Policy Optimisation","created":"2018-06-14","cited_by_count":328},{"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":"1903.08792","title":"End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Tasks","created":"2019-03-21","cited_by_count":289},{"id":"1810.13400","title":"Differentiable MPC for End-to-end Planning and Control","created":"2018-10-31","cited_by_count":189},{"id":"2103.06257","title":"Maximum Entropy RL (Provably) Solves Some Robust RL Problems","created":"2021-03-10","cited_by_count":176},{"id":"1907.02057","title":"Benchmarking Model-Based Reinforcement Learning","created":"2019-07-03","cited_by_count":162},{"id":"1806.09460","title":"A Tour of Reinforcement Learning: The View from Continuous Control","created":"2018-06-25","cited_by_count":151},{"id":"1812.05506","title":"A predictive safety filter for learning-based control of constrained nonlinear dynamical systems","created":"2018-12-13","cited_by_count":118},{"id":"1811.01848","title":"Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control","created":"2018-11-05","cited_by_count":113},{"id":"2310.10943","title":"Reaching the Limit in Autonomous Racing: Optimal Control versus Reinforcement Learning","created":"2023-10-17","cited_by_count":111},{"id":"1705.10702","title":"Cautious Model Predictive Control using Gaussian Process Regression","created":"2017-05-30","cited_by_count":91},{"id":"1906.08649","title":"Exploring Model-based Planning with Policy Networks","created":"2019-06-20","cited_by_count":90},{"id":"1906.04005","title":"Safe Reinforcement Learning Using Robust MPC","created":"2019-06-10","cited_by_count":85},{"id":"2202.06558","title":"Saute RL: Almost Surely Safe Reinforcement Learning Using State Augmentation","created":"2022-02-14","cited_by_count":69},{"id":"1904.04152","title":"Data-driven Economic NMPC using Reinforcement Learning","created":"2019-04-08","cited_by_count":68},{"id":"1910.13753","title":"acados: a modular open-source framework for fast embedded optimal control","created":"2019-10-30","cited_by_count":68},{"id":"1907.03613","title":"Data Efficient Reinforcement Learning for Legged Robots","created":"2019-07-08","cited_by_count":63},{"id":"2306.00577","title":"TorchRL: A data-driven decision-making library for PyTorch","created":"2023-06-01","cited_by_count":60},{"id":"2102.13651","title":"On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning","created":"2021-02-26","cited_by_count":59},{"id":"1806.10644","title":"Efficient representation and approximation of model predictive control laws via deep learning","created":"2018-06-27","cited_by_count":58},{"id":"1901.09732","title":"Making Deep Q-learning methods robust to time discretization","created":"2019-01-28","cited_by_count":58},{"id":"1806.04167","title":"Learning an Approximate Model Predictive Controller with Guarantees","created":"2018-06-11","cited_by_count":57},{"id":"2309.15462","title":"DTC: Deep Tracking Control","created":"2023-09-27","cited_by_count":56},{"id":"1910.10885","title":"Robust Model Predictive Shielding for Safe Reinforcement Learning with Stochastic Dynamics","created":"2019-10-24","cited_by_count":47},{"id":"1901.03737","title":"Low Level Control of a Quadrotor with Deep Model-Based Reinforcement Learning","created":"2019-01-11","cited_by_count":44},{"id":"2003.01239","title":"Rapidly Adaptable Legged Robots via Evolutionary Meta-Learning","created":"2020-03-02","cited_by_count":43},{"id":"2102.11941","title":"State Augmented Constrained Reinforcement Learning: Overcoming the Limitations of Learning with Rewards","created":"2021-02-23","cited_by_count":40},{"id":"1811.05890","title":"Data-Enabled Predictive Control: In the Shallows of the DeePC","created":"2018-11-14","cited_by_count":38},{"id":"2106.03273","title":"Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiation","created":"2021-06-06","cited_by_count":35},{"id":"1909.04947","title":"Crocoddyl: An Efficient and Versatile Framework for Multi-Contact Optimal Control","created":"2019-09-11","cited_by_count":34},{"id":"1909.05197","title":"MPC-Net: A First Principles Guided Policy Search","created":"2019-09-11","cited_by_count":34},{"id":"2004.00915","title":"Safe Reinforcement Learning via Projection on a Safe Set: How to Achieve Optimality?","created":"2020-04-02","cited_by_count":34},{"id":"2004.08763","title":"Model-Predictive Control via Cross-Entropy and Gradient-Based Optimization","created":"2020-04-19","cited_by_count":32},{"id":"2012.05909","title":"Blending MPC & Value Function Approximation for Efficient Reinforcement Learning","created":"2020-12-10","cited_by_count":32},{"id":"2201.02373","title":"Mirror Learning: A Unifying Framework of Policy Optimisation","created":"2022-01-07","cited_by_count":31},{"id":"2102.13073","title":"Where to go next: Learning a Subgoal Recommendation Policy for Navigation Among Pedestrians","created":"2021-02-25","cited_by_count":28},{"id":"2103.13842","title":"Model Predictive Actor-Critic: Accelerating Robot Skill Acquisition with Deep Reinforcement Learning","created":"2021-03-25","cited_by_count":28},{"id":"2305.17842","title":"RL + Model-based Control: Using On-demand Optimal Control to Learn Versatile Legged Locomotion","created":"2023-05-29","cited_by_count":26},{"id":"2002.12174","title":"Optimistic Exploration even with a Pessimistic Initialisation","created":"2020-02-26","cited_by_count":25},{"id":"2003.02547","title":"HPIPM: a high-performance quadratic programming framework for model predictive control","created":"2020-03-05","cited_by_count":23},{"id":"1910.12047","title":"Comparison of Deep Reinforcement Learning and Model Predictive Control for Adaptive Cruise Control","created":"2019-10-26","cited_by_count":22},{"id":"1707.02515","title":"A Fast Integrated Planning and Control Framework for Autonomous Driving via Imitation Learning","created":"2017-07-09","cited_by_count":20},{"id":"1910.03358","title":"Deep Value Model Predictive Control","created":"2019-10-08","cited_by_count":20},{"id":"2102.11907","title":"A predictive safety filter for learning-based racing control","created":"2021-02-23","cited_by_count":20},{"id":"2112.13941","title":"Safe Reinforcement Learning with Chance-constrained Model Predictive Control","created":"2021-12-27","cited_by_count":20},{"id":"1306.3203","title":"Bregman Alternating Direction Method of Multipliers","created":"2013-06-13","cited_by_count":19},{"id":"2103.14331","title":"Imitation Learning from MPC for Quadrupedal Multi-Gait Control","created":"2021-03-26","cited_by_count":18},{"id":"1904.04614","title":"Practical Reinforcement Learning of Stabilizing Economic MPC","created":"2019-04-09","cited_by_count":17},{"id":"2003.03200","title":"Practical Reinforcement Learning For MPC: Learning from sparse objectives in under an hour on a real robot","created":"2020-03-06","cited_by_count":17},{"id":"2008.01712","title":"Deep Inverse Q-learning with Constraints","created":"2020-08-04","cited_by_count":17},{"id":"2404.07099","title":"Rethinking Out-of-Distribution Detection for Reinforcement Learning: Advancing Methods for Evaluation and Detection","created":"2024-04-10","cited_by_count":17},{"id":"2210.12312","title":"Bounded-Regret MPC via Perturbation Analysis: Prediction Error, Constraints, and Nonlinearity","created":"2022-10-22","cited_by_count":16},{"id":"2110.03363","title":"Evaluating model-based planning and planner amortization for continuous control","created":"2021-10-07","cited_by_count":15},{"id":"2312.05873","title":"Learning for CasADi: Data-driven Models in Numerical Optimization","created":"2023-12-10","cited_by_count":15},{"id":"2403.14508","title":"Constrained Reinforcement Learning with Smoothed Log Barrier Function","created":"2024-03-21","cited_by_count":15},{"id":"1911.10789","title":"A Neural Network Architecture to Learn Explicit MPC Controllers from Data","created":"2019-11-25","cited_by_count":14},{"id":"2012.07369","title":"Learning for MPC with Stability & Safety Guarantees","created":"2020-12-14","cited_by_count":14},{"id":"2110.01388","title":"Neural Network Verification in Control","created":"2021-09-30","cited_by_count":14},{"id":"2206.14049","title":"TAMOLS: Terrain-Aware Motion Optimization for Legged Systems","created":"2022-06-28","cited_by_count":14},{"id":"2004.01430","title":"Reinforcement Learning for Mixed-Integer Problems Based on MPC","created":"2020-04-03","cited_by_count":12},{"id":"2208.03520","title":"Recurrent networks, hidden states and beliefs in partially observable environments","created":"2022-08-06","cited_by_count":12},{"id":"2211.06625","title":"CACTO: Continuous Actor-Critic with Trajectory Optimization -- Towards global optimality","created":"2022-11-12","cited_by_count":12},{"id":"2303.06110","title":"Reinforcement Learning Versus Model Predictive Control on Greenhouse Climate Control","created":"2023-03-10","cited_by_count":12},{"id":"2206.13374","title":"Stability Verification of Neural Network Controllers using Mixed-Integer Programming","created":"2022-06-27","cited_by_count":11},{"id":"2211.13779","title":"Learning to Play Trajectory Games Against Opponents with Unknown Objectives","created":"2022-11-24","cited_by_count":11},{"id":"2212.02603","title":"Learning to Optimize in Model Predictive Control","created":"2022-12-05","cited_by_count":11},{"id":"2104.09785","title":"Model-predictive control and reinforcement learning in multi-energy system case studies","created":"2021-04-20","cited_by_count":10},{"id":"2212.11365","title":"End-to-End Imitation Learning with Safety Guarantees using Control Barrier Functions","created":"2022-12-21","cited_by_count":10},{"id":"1908.00177","title":"Learning When to Drive in Intersections by Combining Reinforcement Learning and Model Predictive Control","created":"2019-08-01","cited_by_count":9},{"id":"2103.11949","title":"Reinforcement Learning based on Scenario-tree MPC for ASVs","created":"2021-03-22","cited_by_count":8},{"id":"2104.02863","title":"The Value of Planning for Infinite-Horizon Model Predictive Control","created":"2021-04-07","cited_by_count":8},{"id":"1709.06487","title":"A Simple and Efficient Algorithm for Nonlinear Model Predictive Control","created":"2017-09-19","cited_by_count":7},{"id":"2212.01607","title":"A Hierarchical Approach for Strategic Motion Planning in Autonomous Racing","created":"2022-12-03","cited_by_count":7},{"id":"2210.09206","title":"Model Predictive Control via On-Policy Imitation Learning","created":"2022-10-17","cited_by_count":6},{"id":"2311.04303","title":"Adaptive Stochastic Nonlinear Model Predictive Control with Look-ahead Deep Reinforcement Learning for Autonomous Vehicle Motion Control","created":"2023-11-07","cited_by_count":6},{"id":"2402.13038","title":"N-MPC for Deep Neural Network-Based Collision Avoidance exploiting Depth Images","created":"2024-02-20","cited_by_count":6},{"id":"1809.05802","title":"LVIS: Learning from Value Function Intervals for Contact-Aware Robot Controllers","created":"2018-09-16","cited_by_count":5},{"id":"1903.06804","title":"Regularized and Distributionally Robust Data-Enabled Predictive Control","created":"2019-03-15","cited_by_count":5},{"id":"2101.11331","title":"OffCon$^3$: What is state of the art anyway?","created":"2021-01-27","cited_by_count":5},{"id":"2102.01383","title":"Stability-Constrained Markov Decision Processes Using MPC","created":"2021-02-02","cited_by_count":5},{"id":"2103.11871","title":"Reinforcement Learning based on MPC/MHE for Unmodeled and Partially Observable Dynamics","created":"2021-03-22","cited_by_count":5},{"id":"2209.09006","title":"Enforcing the consensus between Trajectory Optimization and Policy Learning for precise robot control","created":"2022-09-19","cited_by_count":5}],"next_cursor":"100"}