{"list":"other","total":72,"rows":[{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"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":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"1611.07725","title":"iCaRL: Incremental Classifier and Representation Learning","created":"2016-11-23","cited_by_count":2333},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"1905.00414","title":"Similarity of Neural Network Representations Revisited","created":"2019-05-01","cited_by_count":1755},{"id":"1606.04671","title":"Progressive Neural Networks","created":"2016-06-15","cited_by_count":1361},{"id":"2110.06169","title":"Offline Reinforcement Learning with Implicit Q-Learning","created":"2021-10-12","cited_by_count":1293},{"id":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"1910.10897","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","created":"2019-10-24","cited_by_count":1204},{"id":"1711.09601","title":"Memory Aware Synapses: Learning what (not) to forget","created":"2017-11-27","cited_by_count":1105},{"id":"1811.11682","title":"Experience Replay for Continual Learning","created":"2018-11-28","cited_by_count":1095},{"id":"1810.12894","title":"Exploration by Random Network Distillation","created":"2018-10-30","cited_by_count":993},{"id":"1711.05769","title":"PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning","created":"2017-11-15","cited_by_count":898},{"id":"2308.08747","title":"An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning","created":"2023-08-17","cited_by_count":639},{"id":"2008.11687","title":"What is being transferred in transfer learning?","created":"2020-08-26","cited_by_count":368},{"id":"2302.02948","title":"Efficient Online Reinforcement Learning with Offline Data","created":"2023-02-06","cited_by_count":363},{"id":"1708.02072","title":"Measuring Catastrophic Forgetting in Neural Networks","created":"2017-08-07","cited_by_count":360},{"id":"2206.11795","title":"Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos","created":"2022-06-23","cited_by_count":345},{"id":"1709.06009","title":"Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents","created":"2017-09-18","cited_by_count":269},{"id":"2009.08319","title":"Decoupling Representation Learning from Reinforcement Learning","created":"2020-09-14","cited_by_count":269},{"id":"2303.05479","title":"Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning","created":"2023-03-09","cited_by_count":237},{"id":"2312.12148","title":"Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment","created":"2023-12-19","cited_by_count":230},{"id":"2107.00591","title":"Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble","created":"2021-07-01","cited_by_count":214},{"id":"2205.15241","title":"Multi-Game Decision Transformers","created":"2022-05-30","cited_by_count":214},{"id":"2006.13760","title":"The NetHack Learning Environment","created":"2020-06-24","cited_by_count":198},{"id":"1511.06342","title":"Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning","created":"2015-11-19","cited_by_count":178},{"id":"2007.07400","title":"Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics","created":"2020-07-14","cited_by_count":161},{"id":"2105.10919","title":"Continual World: A Robotic Benchmark For Continual Reinforcement Learning","created":"2021-05-23","cited_by_count":116},{"id":"2203.13880","title":"Reinforcement Learning with Action-Free Pre-Training from Videos","created":"2022-03-25","cited_by_count":108},{"id":"2106.04799","title":"Pretraining Representations for Data-Efficient Reinforcement Learning","created":"2021-06-09","cited_by_count":105},{"id":"2310.00166","title":"Motif: Intrinsic Motivation from Artificial Intelligence Feedback","created":"2023-09-29","cited_by_count":102},{"id":"2010.05595","title":"Rethinking Experience Replay: a Bag of Tricks for Continual Learning","created":"2020-10-12","cited_by_count":94},{"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":"2012.12631","title":"Efficient Continual Learning with Modular Networks and Task-Driven Priors","created":"2020-12-23","cited_by_count":88},{"id":"2107.04384","title":"Continual Learning in the Teacher-Student Setup: Impact of Task Similarity","created":"2021-07-09","cited_by_count":88},{"id":"1803.03835","title":"Kickstarting Deep Reinforcement Learning","created":"2018-03-10","cited_by_count":81},{"id":"2205.09588","title":"How catastrophic can catastrophic forgetting be in linear regression?","created":"2022-05-19","cited_by_count":81},{"id":"1712.00378","title":"Time Limits in Reinforcement Learning","created":"2017-12-01","cited_by_count":79},{"id":"2011.14826","title":"Revisiting Rainbow: Promoting more Insightful and Inclusive Deep Reinforcement Learning Research","created":"2020-11-20","cited_by_count":78},{"id":"2210.05178","title":"Pre-Training for Robots: Offline RL Enables Learning New Tasks from a Handful of Trials","created":"2022-10-11","cited_by_count":78},{"id":"2107.10253","title":"Demonstration-Guided Reinforcement Learning with Learned Skills","created":"2021-07-21","cited_by_count":76},{"id":"2010.16402","title":"Why Do Better Loss Functions Lead to Less Transferable Features?","created":"2020-10-30","cited_by_count":73},{"id":"2206.01626","title":"Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress","created":"2022-06-03","cited_by_count":65},{"id":"2111.07736","title":"Continual Learning via Local Module Composition","created":"2021-11-15","cited_by_count":63},{"id":"2202.08938","title":"Improving Intrinsic Exploration with Language Abstractions","created":"2022-02-17","cited_by_count":49},{"id":"2202.00275","title":"Architecture Matters in Continual Learning","created":"2022-02-01","cited_by_count":46},{"id":"2009.11997","title":"Continual Model-Based Reinforcement Learning with Hypernetworks","created":"2020-09-25","cited_by_count":44},{"id":"2106.02940","title":"Same State, Different Task: Continual Reinforcement Learning without Interference","created":"2021-06-05","cited_by_count":43},{"id":"2306.03586","title":"Language acquisition: do children and language models follow similar learning stages?","created":"2023-06-06","cited_by_count":41},{"id":"1904.11455","title":"Ray Interference: a Source of Plateaus in Deep Reinforcement Learning","created":"2019-04-25","cited_by_count":40},{"id":"2207.00429","title":"Modular Lifelong Reinforcement Learning via Neural Composition","created":"2022-07-01","cited_by_count":40},{"id":"2303.07693","title":"Adaptive Policy Learning for Offline-to-Online Reinforcement Learning","created":"2023-03-14","cited_by_count":40},{"id":"1907.05855","title":"DisCoRL: Continual Reinforcement Learning via Policy Distillation","created":"2019-07-11","cited_by_count":36},{"id":"2305.18882","title":"What is Essential for Unseen Goal Generalization of Offline Goal-conditioned RL?","created":"2023-05-30","cited_by_count":36},{"id":"2203.15243","title":"Fine-tuning Image Transformers using Learnable Memory","created":"2022-03-29","cited_by_count":34},{"id":"2209.13900","title":"Disentangling Transfer in Continual Reinforcement Learning","created":"2022-09-28","cited_by_count":33},{"id":"2103.03216","title":"Continuous Coordination As a Realistic Scenario for Lifelong Learning","created":"2021-03-04","cited_by_count":32},{"id":"2211.10445","title":"Building a Subspace of Policies for Scalable Continual Learning","created":"2022-11-18","cited_by_count":28},{"id":"2401.12617","title":"The Joint Effect of Task Similarity and Overparameterization on Catastrophic Forgetting -- An Analytical Model","created":"2024-01-23","cited_by_count":26},{"id":"2212.11110","title":"Lifelong Reinforcement Learning with Modulating Masks","created":"2022-12-21","cited_by_count":22},{"id":"2203.11889","title":"Insights From the NeurIPS 2021 NetHack Challenge","created":"2022-03-22","cited_by_count":20},{"id":"2206.03271","title":"On the Effectiveness of Fine-tuning Versus Meta-reinforcement Learning","created":"2022-06-07","cited_by_count":19},{"id":"2211.11747","title":"NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research","created":"2022-11-15","cited_by_count":18},{"id":"2211.00539","title":"Dungeons and Data: A Large-Scale NetHack Dataset","created":"2022-11-01","cited_by_count":16},{"id":"2305.19240","title":"NetHack is Hard to Hack","created":"2023-05-30","cited_by_count":11},{"id":"2205.03353","title":"How to Spend Your Robot Time: Bridging Kickstarting and Offline Reinforcement Learning for Vision-based Robotic Manipulation","created":"2022-05-06","cited_by_count":9},{"id":"2210.12448","title":"Probing Transfer in Deep Reinforcement Learning without Task Engineering","created":"2022-10-22","cited_by_count":4}],"next_cursor":null}