{"list":"other","total":63,"rows":[{"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":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"1703.06907","title":"Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World","created":"2017-03-20","cited_by_count":1498},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"2004.05439","title":"Meta-Learning in Neural Networks: A Survey","created":"2020-04-11","cited_by_count":950},{"id":"1703.02910","title":"Deep Bayesian Active Learning with Image Data","created":"2017-03-08","cited_by_count":819},{"id":"2009.00236","title":"A Survey of Deep Active Learning","created":"2020-08-30","cited_by_count":554},{"id":"1909.04630","title":"Meta-Learning with Implicit Gradients","created":"2019-09-10","cited_by_count":525},{"id":"1611.02779","title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning","created":"2016-11-09","cited_by_count":503},{"id":"1902.06705","title":"On Evaluating Adversarial Robustness","created":"2019-02-18","cited_by_count":447},{"id":"1906.08158","title":"BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning","created":"2019-06-19","cited_by_count":432},{"id":"1903.08254","title":"Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables","created":"2019-03-19","cited_by_count":389},{"id":"1710.10628","title":"Variational Continual Learning","created":"2017-10-29","cited_by_count":339},{"id":"1512.01629","title":"Risk-Constrained Reinforcement Learning with Percentile Risk Criteria","created":"2015-12-05","cited_by_count":337},{"id":"1807.01622","title":"Neural Processes","created":"2018-07-04","cited_by_count":311},{"id":"2012.02096","title":"Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design","created":"2020-12-03","cited_by_count":275},{"id":"1301.2609","title":"Learning to Optimize Via Posterior Sampling","created":"2013-01-11","cited_by_count":256},{"id":"1806.02817","title":"Probabilistic Model-Agnostic Meta-Learning","created":"2018-06-07","cited_by_count":256},{"id":"1306.0940","title":"(More) Efficient Reinforcement Learning via Posterior Sampling","created":"2013-06-04","cited_by_count":233},{"id":"2410.00425","title":"ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI","created":"2024-10-01","cited_by_count":229},{"id":"1910.08348","title":"VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning","created":"2019-10-18","cited_by_count":217},{"id":"2102.11582","title":"Deep Deterministic Uncertainty: A Simple Baseline","created":"2021-02-23","cited_by_count":200},{"id":"1806.03836","title":"Bayesian Model-Agnostic Meta-Learning","created":"2018-06-11","cited_by_count":194},{"id":"1506.02188","title":"Risk-Sensitive and Robust Decision-Making: a CVaR Optimization Approach","created":"2015-06-06","cited_by_count":170},{"id":"1904.04762","title":"Active Domain Randomization","created":"2019-04-09","cited_by_count":170},{"id":"2112.05077","title":"Generating Useful Accident-Prone Driving Scenarios via a Learned Traffic Prior","created":"2021-12-09","cited_by_count":139},{"id":"1802.07245","title":"Meta-Reinforcement Learning of Structured Exploration Strategies","created":"2018-02-20","cited_by_count":130},{"id":"2110.02439","title":"Replay-Guided Adversarial Environment Design","created":"2021-10-06","cited_by_count":111},{"id":"2301.08028","title":"A Tutorial on Meta-Reinforcement Learning","created":"2023-01-19","cited_by_count":108},{"id":"2406.01967","title":"DrEureka: Language Model Guided Sim-To-Real Transfer","created":"2024-06-04","cited_by_count":83},{"id":"1502.03919","title":"Policy Gradient for Coherent Risk Measures","created":"2015-02-13","cited_by_count":76},{"id":"2206.03996","title":"Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learning","created":"2022-06-08","cited_by_count":58},{"id":"1904.00511","title":"Risk Averse Robust Adversarial Reinforcement Learning","created":"2019-03-31","cited_by_count":57},{"id":"2204.07965","title":"Entropy-based Active Learning for Object Detection with Progressive Diversity Constraint","created":"2022-04-17","cited_by_count":53},{"id":"1307.6769","title":"Streaming Variational Bayes","created":"2013-07-25","cited_by_count":48},{"id":"2003.02471","title":"Data-efficient Domain Randomization with Bayesian Optimization","created":"2020-03-05","cited_by_count":47},{"id":"2205.05138","title":"Efficient Risk-Averse Reinforcement Learning","created":"2022-05-10","cited_by_count":43},{"id":"1505.04627","title":"Simple regret for infinitely many armed bandits","created":"2015-05-18","cited_by_count":39},{"id":"2008.09469","title":"Doubly Stochastic Variational Inference for Neural Processes with Hierarchical Latent Variables","created":"2020-08-21","cited_by_count":33},{"id":"2102.05762","title":"Risk-Averse Bayes-Adaptive Reinforcement Learning","created":"2021-02-10","cited_by_count":29},{"id":"2407.13237","title":"LLM-Empowered State Representation for Reinforcement Learning","created":"2024-07-18","cited_by_count":28},{"id":"1805.09692","title":"Been There, Done That: Meta-Learning with Episodic Recall","created":"2018-05-24","cited_by_count":26},{"id":"2310.04413","title":"Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets","created":"2023-10-06","cited_by_count":24},{"id":"2412.11120","title":"Latent Reward: LLM-Empowered Credit Assignment in Episodic Reinforcement Learning","created":"2024-12-15","cited_by_count":23},{"id":"2411.07934","title":"Doubly Mild Generalization for Offline Reinforcement Learning","created":"2024-11-12","cited_by_count":21},{"id":"2501.11039","title":"Model Predictive Task Sampling for Efficient and Robust Adaptation","created":"2025-01-19","cited_by_count":21},{"id":"2311.08935","title":"Supported Trust Region Optimization for Offline Reinforcement Learning","created":"2023-11-15","cited_by_count":20},{"id":"2311.01885","title":"Domain Randomization via Entropy Maximization","created":"2023-11-03","cited_by_count":19},{"id":"2102.08291","title":"Model-based Meta Reinforcement Learning using Graph Structured Surrogate Models","created":"2021-02-16","cited_by_count":17},{"id":"2106.06326","title":"TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation","created":"2021-06-11","cited_by_count":17},{"id":"2410.19400","title":"Offline Reinforcement Learning with OOD State Correction and OOD Action Suppression","created":"2024-10-25","cited_by_count":17},{"id":"2311.09191","title":"Domain Aligned CLIP for Few-shot Classification","created":"2023-11-15","cited_by_count":16},{"id":"2407.19523","title":"Robust Fast Adaptation from Adversarially Explicit Task Distribution Generation","created":"2024-07-28","cited_by_count":13},{"id":"2301.11147","title":"Train Hard, Fight Easy: Robust Meta Reinforcement Learning","created":"2023-01-26","cited_by_count":12},{"id":"2408.10556","title":"Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks","created":"2024-08-20","cited_by_count":11},{"id":"2310.00708","title":"A Simple Yet Effective Strategy to Robustify the Meta Learning Paradigm","created":"2023-10-01","cited_by_count":10},{"id":"1602.05130","title":"Risk Aversion in Finite Markov Decision Processes Using Total Cost Criteria and Average Value at Risk","created":"2016-02-16","cited_by_count":9},{"id":"2410.02511","title":"Stop Wandering, Find the Keys: LLMs Discriminate Key States for Efficient Multi-Agent Exploration","created":"2024-10-03","cited_by_count":9},{"id":"2501.03264","title":"Bridge the Inference Gaps of Neural Processes via Expectation Maximization","created":"2025-01-04","cited_by_count":8},{"id":"2410.22788","title":"Theoretical Investigations and Practical Enhancements on Tail Task Risk Minimization in Meta Learning","created":"2024-10-30","cited_by_count":4},{"id":"2301.02053","title":"Max-Min Diversification with Fairness Constraints: Exact and Approximation Algorithms","created":"2023-01-05","cited_by_count":2}],"next_cursor":null}