{"list":"other","total":66,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"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":"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":"1707.01495","title":"Hindsight Experience Replay","created":"2017-07-05","cited_by_count":1136},{"id":"1810.12894","title":"Exploration by Random Network Distillation","created":"2018-10-30","cited_by_count":993},{"id":"1801.00690","title":"DeepMind Control Suite","created":"2018-01-02","cited_by_count":956},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"1503.02406","title":"Deep Learning and the Information Bottleneck Principle","created":"2015-03-09","cited_by_count":802},{"id":"1710.06537","title":"Sim-to-Real Transfer of Robotic Control with Dynamics Randomization","created":"2017-10-18","cited_by_count":672},{"id":"1606.01868","title":"Unifying Count-Based Exploration and Intrinsic Motivation","created":"2016-06-06","cited_by_count":639},{"id":"2104.02008","title":"Domain Generalization with MixStyle","created":"2021-04-05","cited_by_count":566},{"id":"2004.14990","title":"Reinforcement Learning with Augmented Data","created":"2020-04-30","cited_by_count":468},{"id":"1507.06527","title":"Deep Recurrent Q-Learning for Partially Observable MDPs","created":"2015-07-23","cited_by_count":465},{"id":"2105.03075","title":"A Survey of Data Augmentation Approaches for NLP","created":"2021-05-07","cited_by_count":409},{"id":"1812.02341","title":"Quantifying Generalization in Reinforcement Learning","created":"2018-12-06","cited_by_count":352},{"id":"2306.13831","title":"Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks","created":"2023-06-24","cited_by_count":327},{"id":"1803.00933","title":"Distributed Prioritized Experience Replay","created":"2018-03-02","cited_by_count":269},{"id":"2004.12919","title":"First return, then explore","created":"2020-04-27","cited_by_count":266},{"id":"1703.01310","title":"Count-Based Exploration with Neural Density Models","created":"2017-03-03","cited_by_count":257},{"id":"1611.04201","title":"CAD2RL: Real Single-Image Flight without a Single Real Image","created":"2016-11-13","cited_by_count":233},{"id":"1502.02259","title":"Contextual Markov Decision Processes","created":"2015-02-08","cited_by_count":220},{"id":"1806.03335","title":"Randomized Prior Functions for Deep Reinforcement Learning","created":"2018-06-08","cited_by_count":219},{"id":"2111.09794","title":"A Survey of Zero-shot Generalisation in Deep Reinforcement Learning","created":"2021-11-18","cited_by_count":170},{"id":"2205.00824","title":"Exploration in Deep Reinforcement Learning: A Survey","created":"2022-05-02","cited_by_count":166},{"id":"2201.08299","title":"Goal-Conditioned Reinforcement Learning: Problems and Solutions","created":"2022-01-20","cited_by_count":158},{"id":"1703.07608","title":"Deep Exploration via Randomized Value Functions","created":"2017-03-22","cited_by_count":156},{"id":"2011.13389","title":"Generalization in Reinforcement Learning by Soft Data Augmentation","created":"2020-11-26","cited_by_count":137},{"id":"2002.12292","title":"RIDE: Rewarding Impact-Driven Exploration for Procedurally-Generated Environments","created":"2020-02-27","cited_by_count":135},{"id":"2004.12570","title":"The Ingredients of Real-World Robotic Reinforcement Learning","created":"2020-04-27","cited_by_count":117},{"id":"1402.0635","title":"Generalization and Exploration via Randomized Value Functions","created":"2014-02-04","cited_by_count":112},{"id":"1910.05396","title":"Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning","created":"2019-10-11","cited_by_count":104},{"id":"1910.12911","title":"Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck","created":"2019-10-28","cited_by_count":101},{"id":"2109.13202","title":"MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research","created":"2021-09-27","cited_by_count":97},{"id":"2006.11751","title":"Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement Learning","created":"2020-06-21","cited_by_count":93},{"id":"2006.12122","title":"Learning with AMIGo: Adversarially Motivated Intrinsic Goals","created":"2020-06-22","cited_by_count":88},{"id":"1806.01830","title":"Relational Deep Reinforcement Learning","created":"2018-06-05","cited_by_count":73},{"id":"1706.04317","title":"Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics","created":"2017-06-14","cited_by_count":58},{"id":"1809.03470","title":"ViZDoom Competitions: Playing Doom from Pixels","created":"2018-09-10","cited_by_count":51},{"id":"2210.05805","title":"Exploration via Elliptical Episodic Bonuses","created":"2022-10-11","cited_by_count":51},{"id":"2109.02869","title":"The Sensory Neuron as a Transformer: Permutation-Invariant Neural Networks for Reinforcement Learning","created":"2021-09-07","cited_by_count":50},{"id":"2003.08165","title":"Neuroevolution of Self-Interpretable Agents","created":"2020-03-18","cited_by_count":49},{"id":"2106.07841","title":"Randomized Exploration for Reinforcement Learning with General Value Function Approximation","created":"2021-06-15","cited_by_count":49},{"id":"2005.00695","title":"On the Generalization Effects of Linear Transformations in Data Augmentation","created":"2020-05-02","cited_by_count":47},{"id":"2102.04376","title":"Adversarially Guided Actor-Critic","created":"2021-02-08","cited_by_count":47},{"id":"2106.10268","title":"MADE: Exploration via Maximizing Deviation from Explored Regions","created":"2021-06-18","cited_by_count":40},{"id":"2210.06441","title":"How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization","created":"2022-10-12","cited_by_count":40},{"id":"2111.13119","title":"Interesting Object, Curious Agent: Learning Task-Agnostic Exploration","created":"2021-11-25","cited_by_count":38},{"id":"2306.05483","title":"On the Importance of Exploration for Generalization in Reinforcement Learning","created":"2023-06-08","cited_by_count":31},{"id":"2104.02921","title":"Unsupervised Visual Attention and Invariance for Reinforcement Learning","created":"2021-04-07","cited_by_count":30},{"id":"2109.03214","title":"Robust Predictable Control","created":"2021-09-07","cited_by_count":29},{"id":"2008.00614","title":"Dynamics Generalization via Information Bottleneck in Deep Reinforcement Learning","created":"2020-08-03","cited_by_count":26},{"id":"2210.05021","title":"The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspective","created":"2022-10-10","cited_by_count":24},{"id":"2111.05529","title":"Understanding the Generalization Benefit of Model Invariance from a Data Perspective","created":"2021-11-10","cited_by_count":22},{"id":"2306.03072","title":"Explore to Generalize in Zero-Shot RL","created":"2023-06-05","cited_by_count":20},{"id":"2306.03236","title":"A Study of Global and Episodic Bonuses for Exploration in Contextual MDPs","created":"2023-06-05","cited_by_count":20},{"id":"2206.00051","title":"Learning Instance-Specific Augmentations by Capturing Local Invariances","created":"2022-05-31","cited_by_count":15},{"id":"2210.05409","title":"LECO: Learnable Episodic Count for Task-Specific Intrinsic Reward","created":"2022-10-11","cited_by_count":11},{"id":"2211.10282","title":"Exploring through Random Curiosity with General Value Functions","created":"2022-11-18","cited_by_count":10},{"id":"2306.01460","title":"ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages","created":"2023-06-02","cited_by_count":10},{"id":"2306.02419","title":"Bad Habits: Policy Confounding and Out-of-Trajectory Generalization in RL","created":"2023-06-04","cited_by_count":10},{"id":"2210.09960","title":"Rethinking Value Function Learning for Generalization in Reinforcement Learning","created":"2022-10-18","cited_by_count":8},{"id":"2306.07124","title":"Diverse Projection Ensembles for Distributional Reinforcement Learning","created":"2023-06-12","cited_by_count":8},{"id":"2105.09992","title":"Don't Do What Doesn't Matter: Intrinsic Motivation with Action Usefulness","created":"2021-05-20","cited_by_count":7},{"id":"2107.07394","title":"Explore and Control with Adversarial Surprise","created":"2021-07-12","cited_by_count":6}],"next_cursor":null}