{"list":"other","total":93,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"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":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"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":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1606.03476","title":"Generative Adversarial Imitation Learning","created":"2016-06-10","cited_by_count":1597},{"id":"1610.05492","title":"Federated Learning: Strategies for Improving Communication Efficiency","created":"2016-10-18","cited_by_count":1475},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1511.05952","title":"Prioritized Experience Replay","created":"2015-11-18","cited_by_count":1099},{"id":"1511.06581","title":"Dueling Network Architectures for Deep Reinforcement Learning","created":"2015-11-20","cited_by_count":785},{"id":"1611.02779","title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning","created":"2016-11-09","cited_by_count":503},{"id":"1703.05449","title":"Minimax Regret Bounds for Reinforcement Learning","created":"2017-03-16","cited_by_count":503},{"id":"1710.11248","title":"Learning Robust Rewards with Adversarial Inverse Reinforcement Learning","created":"2017-10-30","cited_by_count":490},{"id":"2009.13303","title":"Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey","created":"2020-09-24","cited_by_count":413},{"id":"1707.08817","title":"Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards","created":"2017-07-27","cited_by_count":319},{"id":"1803.11347","title":"Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning","created":"2018-03-30","cited_by_count":276},{"id":"1803.00933","title":"Distributed Prioritized Experience Replay","created":"2018-03-02","cited_by_count":269},{"id":"2009.07888","title":"Transfer Learning in Deep Reinforcement Learning: A Survey","created":"2020-09-16","cited_by_count":265},{"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":"1611.01224","title":"Sample Efficient Actor-Critic with Experience Replay","created":"2016-11-03","cited_by_count":188},{"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":"1408.2156","title":"Statistical guarantees for the EM algorithm: From population to sample-based analysis","created":"2014-08-09","cited_by_count":133},{"id":"1806.07851","title":"Sim-to-Real Reinforcement Learning for Deformable Object Manipulation","created":"2018-06-20","cited_by_count":131},{"id":"1510.08906","title":"Sample Complexity of Episodic Fixed-Horizon Reinforcement Learning","created":"2015-10-29","cited_by_count":106},{"id":"2108.11887","title":"Federated Reinforcement Learning: Techniques, Applications, and Open Challenges","created":"2021-08-26","cited_by_count":81},{"id":"2005.09382","title":"Human Instruction-Following with Deep Reinforcement Learning via Transfer-Learning from Text","created":"2020-05-19","cited_by_count":59},{"id":"1909.12906","title":"Meta Reinforcement Learning for Sim-to-real Domain Adaptation","created":"2019-09-16","cited_by_count":49},{"id":"2003.02471","title":"Data-efficient Domain Randomization with Bayesian Optimization","created":"2020-03-05","cited_by_count":47},{"id":"1805.11593","title":"Observe and Look Further: Achieving Consistent Performance on Atari","created":"2018-05-29","cited_by_count":44},{"id":"1910.06001","title":"Federated Transfer Reinforcement Learning for Autonomous Driving","created":"2019-10-14","cited_by_count":44},{"id":"2006.13169","title":"Experience Replay with Likelihood-free Importance Weights","created":"2020-06-23","cited_by_count":42},{"id":"2006.14804","title":"Widening the Pipeline in Human-Guided Reinforcement Learning with Explanation and Context-Aware Data Augmentation","created":"2020-06-26","cited_by_count":42},{"id":"1810.11748","title":"DQN-TAMER: Human-in-the-Loop Reinforcement Learning with Intractable Feedback","created":"2018-10-28","cited_by_count":41},{"id":"1709.06683","title":"OptionGAN: Learning Joint Reward-Policy Options using Generative Adversarial Inverse Reinforcement Learning","created":"2017-09-20","cited_by_count":40},{"id":"2101.12446","title":"Counterfactual State Explanations for Reinforcement Learning Agents via Generative Deep Learning","created":"2021-01-29","cited_by_count":39},{"id":"1809.02064","title":"Sample-Efficient Imitation Learning via Generative Adversarial Nets","created":"2018-09-06","cited_by_count":36},{"id":"1902.00778","title":"Certified Reinforcement Learning with Logic Guidance","created":"2019-02-02","cited_by_count":36},{"id":"1802.00265","title":"VR-Goggles for Robots: Real-to-sim Domain Adaptation for Visual Control","created":"2018-02-01","cited_by_count":35},{"id":"2006.13704","title":"Efficient Sampling-Based Maximum Entropy Inverse Reinforcement Learning with Application to Autonomous Driving","created":"2020-06-22","cited_by_count":34},{"id":"2206.09421","title":"Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation","created":"2022-06-19","cited_by_count":31},{"id":"2210.10195","title":"Curriculum Reinforcement Learning using Optimal Transport via Gradual Domain Adaptation","created":"2022-10-18","cited_by_count":28},{"id":"1902.08039","title":"Curiosity-Driven Experience Prioritization via Density Estimation","created":"2019-02-20","cited_by_count":27},{"id":"2101.06005","title":"SimGAN: Hybrid Simulator Identification for Domain Adaptation via Adversarial Reinforcement Learning","created":"2021-01-15","cited_by_count":27},{"id":"2005.11016","title":"Reinforcement learning with human advice: a survey","created":"2020-05-22","cited_by_count":24},{"id":"1701.04079","title":"Agent-Agnostic Human-in-the-Loop Reinforcement Learning","created":"2017-01-15","cited_by_count":23},{"id":"1710.06574","title":"The Effects of Memory Replay in Reinforcement Learning","created":"2017-10-18","cited_by_count":23},{"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":"2203.16792","title":"TrajGen: Generating Realistic and Diverse Trajectories with Reactive and Feasible Agent Behaviors for Autonomous Driving","created":"2022-03-31","cited_by_count":23},{"id":"2206.13316","title":"Humans are not Boltzmann Distributions: Challenges and Opportunities for Modelling Human Feedback and Interaction in Reinforcement Learning","created":"2022-06-27","cited_by_count":22},{"id":"1910.09470","title":"Self-Supervised Sim-to-Real Adaptation for Visual Robotic Manipulation","created":"2019-10-21","cited_by_count":19},{"id":"1909.13111","title":"MULTIPOLAR: Multi-Source Policy Aggregation for Transfer Reinforcement Learning between Diverse Environmental Dynamics","created":"2019-09-28","cited_by_count":18},{"id":"1910.07719","title":"Single Episode Policy Transfer in Reinforcement Learning","created":"2019-10-17","cited_by_count":18},{"id":"2111.00633","title":"Settling the Horizon-Dependence of Sample Complexity in Reinforcement Learning","created":"2021-11-01","cited_by_count":18},{"id":"2203.11653","title":"Transferring Multi-Agent Reinforcement Learning Policies for Autonomous Driving using Sim-to-Real","created":"2022-03-22","cited_by_count":17},{"id":"2011.01891","title":"Policy Transfer via Kinematic Domain Randomization and Adaptation","created":"2020-11-03","cited_by_count":16},{"id":"2207.04361","title":"State Dropout-Based Curriculum Reinforcement Learning for Self-Driving at Unsignalized Intersections","created":"2022-07-10","cited_by_count":16},{"id":"2011.11827","title":"REPAINT: Knowledge Transfer in Deep Reinforcement Learning","created":"2020-11-24","cited_by_count":14},{"id":"2101.02680","title":"Zero-shot sim-to-real transfer of tactile control policies for aggressive swing-up manipulation","created":"2021-01-07","cited_by_count":14},{"id":"2004.14684","title":"Sim-to-Real Transfer with Incremental Environment Complexity for Reinforcement Learning of Depth-Based Robot Navigation","created":"2020-04-30","cited_by_count":13},{"id":"2107.01908","title":"Reward-Adaptive Reinforcement Learning: Dynamic Policy Gradient Optimization for Bipedal Locomotion","created":"2021-07-05","cited_by_count":13},{"id":"1908.08578","title":"On Convergence Rate of Adaptive Multiscale Value Function Approximation For Reinforcement Learning","created":"2019-08-22","cited_by_count":12},{"id":"2003.04956","title":"SQUIRL: Robust and Efficient Learning from Video Demonstration of Long-Horizon Robotic Manipulation Tasks","created":"2020-03-10","cited_by_count":10},{"id":"2203.14477","title":"UNMAS: Multi-Agent Reinforcement Learning for Unshaped Cooperative Scenarios","created":"2022-03-28","cited_by_count":9},{"id":"1902.06239","title":"A new Potential-Based Reward Shaping for Reinforcement Learning Agent","created":"2019-02-17","cited_by_count":8},{"id":"2202.02465","title":"ASHA: Assistive Teleoperation via Human-in-the-Loop Reinforcement Learning","created":"2022-02-05","cited_by_count":8},{"id":"2207.14561","title":"Cyclic Policy Distillation: Sample-Efficient Sim-to-Real Reinforcement Learning with Domain Randomization","created":"2022-07-29","cited_by_count":8},{"id":"2211.03430","title":"A Federated DRL Approach for Smart Micro-Grid Energy Control with Distributed Energy Resources","created":"2022-11-07","cited_by_count":8},{"id":"2008.07353","title":"On the Sample Complexity of Reinforcement Learning with Policy Space Generalization","created":"2020-08-17","cited_by_count":7},{"id":"2111.04698","title":"Interactive Inverse Reinforcement Learning for Cooperative Games","created":"2021-11-08","cited_by_count":7},{"id":"2007.00192","title":"Personalization of Hearing Aid Compression by Human-In-Loop Deep Reinforcement Learning","created":"2020-07-01","cited_by_count":6},{"id":"2007.13715","title":"Point Cloud Based Reinforcement Learning for Sim-to-Real and Partial Observability in Visual Navigation","created":"2020-07-27","cited_by_count":5},{"id":"2103.03446","title":"Enhanced Aspect-Based Sentiment Analysis Models with Progressive Self-supervised Attention Learning","created":"2021-03-05","cited_by_count":5},{"id":"2210.03455","title":"Advice Conformance Verification by Reinforcement Learning agents for Human-in-the-Loop","created":"2022-10-07","cited_by_count":5},{"id":"1911.00238","title":"Situated GAIL: Multitask imitation using task-conditioned adversarial inverse reinforcement learning","created":"2019-11-01","cited_by_count":4},{"id":"2008.13221","title":"Human-in-the-Loop Methods for Data-Driven and Reinforcement Learning Systems","created":"2020-08-30","cited_by_count":4},{"id":"1805.04493","title":"Interactive Reinforcement Learning with Dynamic Reuse of Prior Knowledge from Human/Agent's Demonstration","created":"2018-05-11","cited_by_count":3},{"id":"2007.03961","title":"Double Prioritized State Recycled Experience Replay","created":"2020-07-08","cited_by_count":3},{"id":"2102.02639","title":"Improving Reinforcement Learning with Human Assistance: An Argument for Human Subject Studies with HIPPO Gym","created":"2021-02-02","cited_by_count":3},{"id":"2207.08056","title":"Federated Deep Reinforcement Learning for RIS-Assisted Indoor Multi-Robot Communication Systems","created":"2022-07-17","cited_by_count":3},{"id":"2004.01223","title":"Value Driven Representation for Human-in-the-Loop Reinforcement Learning","created":"2020-04-02","cited_by_count":2},{"id":"2105.04699","title":"Adaptive Policy Transfer in Reinforcement Learning","created":"2021-05-10","cited_by_count":2},{"id":"2208.02932","title":"Human Decision Makings on Curriculum Reinforcement Learning with Difficulty Adjustment","created":"2022-08-04","cited_by_count":2},{"id":"2210.17368","title":"Teacher-student curriculum learning for reinforcement learning","created":"2022-10-31","cited_by_count":2},{"id":"1904.02206","title":"Jointly Pre-training with Supervised, Autoencoder, and Value Losses for Deep Reinforcement Learning","created":"2019-04-03","cited_by_count":1},{"id":"2004.04120","title":"Solving the scalarization issues of Advantage-based Reinforcement Learning Algorithms","created":"2020-04-08","cited_by_count":1},{"id":"2106.10318","title":"Sample Efficient Social Navigation Using Inverse Reinforcement Learning","created":"2021-06-18","cited_by_count":1}],"next_cursor":null}