{"list":"other","total":89,"rows":[{"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":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"id":"1606.04671","title":"Progressive Neural Networks","created":"2016-06-15","cited_by_count":1361},{"id":"1802.07569","title":"Continual Lifelong Learning with Neural Networks: A Review","created":"2018-02-21","cited_by_count":1330},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"1711.05769","title":"PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning","created":"2017-11-15","cited_by_count":898},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"2306.01708","title":"TIES-Merging: Resolving Interference When Merging Models","created":"2023-06-02","cited_by_count":818},{"id":"2004.04136","title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","created":"2020-04-08","cited_by_count":760},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"1801.01423","title":"Overcoming catastrophic forgetting with hard attention to the task","created":"2018-01-04","cited_by_count":681},{"id":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"1605.06676","title":"Learning to Communicate with Deep Multi-Agent Reinforcement Learning","created":"2016-05-21","cited_by_count":575},{"id":"2003.08271","title":"Pre-trained Models for Natural Language Processing: A Survey","created":"2020-03-18","cited_by_count":505},{"id":"1611.02779","title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning","created":"2016-11-09","cited_by_count":503},{"id":"1805.08296","title":"Data-Efficient Hierarchical Reinforcement Learning","created":"2018-05-21","cited_by_count":455},{"id":"1611.05397","title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","created":"2016-11-16","cited_by_count":404},{"id":"1903.08254","title":"Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables","created":"2019-03-19","cited_by_count":389},{"id":"1511.02799","title":"Neural Module Networks","created":"2015-11-09","cited_by_count":376},{"id":"1905.07553","title":"Which Tasks Should Be Learned Together in Multi-task Learning?","created":"2019-05-18","cited_by_count":375},{"id":"2307.13269","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","created":"2023-07-25","cited_by_count":364},{"id":"2105.00243","title":"FedProto: Federated Prototype Learning across Heterogeneous Clients","created":"2021-05-01","cited_by_count":352},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319},{"id":"1906.00695","title":"Continual learning with hypernetworks","created":"2019-06-03","cited_by_count":273},{"id":"2009.08319","title":"Decoupling Representation Learning from Reinforcement Learning","created":"2020-09-14","cited_by_count":269},{"id":"1705.06366","title":"Automatic Goal Generation for Reinforcement Learning Agents","created":"2017-05-17","cited_by_count":259},{"id":"2306.04488","title":"Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards","created":"2023-06-07","cited_by_count":243},{"id":"1802.10269","title":"Selective Experience Replay for Lifelong Learning","created":"2018-02-28","cited_by_count":241},{"id":"1911.13299","title":"What's Hidden in a Randomly Weighted Neural Network?","created":"2019-11-29","cited_by_count":237},{"id":"2212.05055","title":"Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints","created":"2022-12-09","cited_by_count":209},{"id":"2102.11271","title":"Reinforcement Learning with Prototypical Representations","created":"2021-02-22","cited_by_count":179},{"id":"1811.08737","title":"SpotTune: Transfer Learning through Adaptive Fine-tuning","created":"2018-11-21","cited_by_count":168},{"id":"2502.14143","title":"Multi-Agent Risks from Advanced AI","created":"2025-02-19","cited_by_count":163},{"id":"2003.03196","title":"Federated Continual Learning with Weighted Inter-client Transfer","created":"2020-03-06","cited_by_count":161},{"id":"2403.07816","title":"Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM","created":"2024-03-12","cited_by_count":109},{"id":"2109.13202","title":"MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research","created":"2021-09-27","cited_by_count":97},{"id":"2402.16843","title":"Multi-LoRA Composition for Image Generation","created":"2024-02-26","cited_by_count":80},{"id":"2412.10400","title":"Reinforcement Learning Enhanced LLMs: A Survey","created":"2024-12-05","cited_by_count":71},{"id":"2111.07736","title":"Continual Learning via Local Module Composition","created":"2021-11-15","cited_by_count":63},{"id":"1903.00742","title":"Autocurricula and the Emergence of Innovation from Social Interaction: A Manifesto for Multi-Agent Intelligence Research","created":"2019-03-02","cited_by_count":61},{"id":"1806.08295","title":"How Many Random Seeds? Statistical Power Analysis in Deep Reinforcement Learning Experiments","created":"2018-06-21","cited_by_count":60},{"id":"2106.10207","title":"Distributed Deep Learning in Open Collaborations","created":"2021-06-18","cited_by_count":58},{"id":"2006.09430","title":"Wasserstein Embedding for Graph Learning","created":"2020-06-16","cited_by_count":56},{"id":"1806.10166","title":"Modular meta-learning","created":"2018-06-26","cited_by_count":51},{"id":"2311.11385","title":"Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts","created":"2023-11-19","cited_by_count":49},{"id":"1806.06464","title":"Learning Policy Representations in Multiagent Systems","created":"2018-06-17","cited_by_count":48},{"id":"2210.11653","title":"PaCo: Parameter-Compositional Multi-Task Reinforcement Learning","created":"2022-10-21","cited_by_count":46},{"id":"2401.09561","title":"Sharing Knowledge in Multi-Task Deep Reinforcement Learning","created":"2024-01-17","cited_by_count":44},{"id":"1905.05901","title":"Learning What and Where to Transfer","created":"2019-05-15","cited_by_count":43},{"id":"2207.00429","title":"Modular Lifelong Reinforcement Learning via Neural Composition","created":"2022-07-01","cited_by_count":40},{"id":"2007.07732","title":"Lifelong Learning of Compositional Structures","created":"2020-07-15","cited_by_count":35},{"id":"2209.13900","title":"Disentangling Transfer in Continual Reinforcement Learning","created":"2022-09-28","cited_by_count":33},{"id":"2006.04338","title":"A Decentralized Policy Gradient Approach to Multi-task Reinforcement Learning","created":"2020-06-08","cited_by_count":25},{"id":"2102.12571","title":"The Logical Options Framework","created":"2021-02-24","cited_by_count":25},{"id":"2208.11726","title":"Wasserstein Task Embedding for Measuring Task Similarities","created":"2022-08-24","cited_by_count":25},{"id":"2407.07852","title":"OpenDiLoCo: An Open-Source Framework for Globally Distributed Low-Communication Training","created":"2024-07-10","cited_by_count":24},{"id":"2212.11110","title":"Lifelong Reinforcement Learning with Modulating Masks","created":"2022-12-21","cited_by_count":22},{"id":"1902.05179","title":"Multi-task learning with compressible features for Collaborative Intelligence","created":"2019-02-14","cited_by_count":20},{"id":"2109.08665","title":"DiNNO: Distributed Neural Network Optimization for Multi-Robot Collaborative Learning","created":"2021-09-17","cited_by_count":16},{"id":"1905.03329","title":"Learning Embeddings into Entropic Wasserstein Spaces","created":"2019-05-08","cited_by_count":15},{"id":"1709.05412","title":"Multi-Agent Distributed Lifelong Learning for Collective Knowledge Acquisition","created":"2017-09-15","cited_by_count":13},{"id":"1902.04999","title":"Wasserstein Barycenter Model Ensembling","created":"2019-02-13","cited_by_count":10},{"id":"2305.10997","title":"Sharing Lifelong Reinforcement Learning Knowledge via Modulating Masks","created":"2023-05-18","cited_by_count":10},{"id":"2211.03352","title":"Curriculum-based Asymmetric Multi-task Reinforcement Learning","created":"2022-11-07","cited_by_count":8},{"id":"2201.13361","title":"Signing the Supermask: Keep, Hide, Invert","created":"2022-01-31","cited_by_count":7},{"id":"2206.13720","title":"SHELS: Exclusive Feature Sets for Novelty Detection and Continual Learning Without Class Boundaries","created":"2022-06-28","cited_by_count":7},{"id":"2305.15591","title":"Lightweight Learner for Shared Knowledge Lifelong Learning","created":"2023-05-24","cited_by_count":7},{"id":"2405.19047","title":"Statistical Context Detection for Deep Lifelong Reinforcement Learning","created":"2024-05-29","cited_by_count":7},{"id":"2405.12308","title":"Continual Deep Reinforcement Learning for Decentralized Satellite Routing","created":"2024-05-20","cited_by_count":6},{"id":"2302.07958","title":"Meta-Reinforcement Learning via Exploratory Task Clustering","created":"2023-02-15","cited_by_count":4},{"id":"2302.10887","title":"The configurable tree graph (CT-graph): measurable problems in partially observable and distal reward environments for lifelong reinforcement learning","created":"2023-01-21","cited_by_count":4},{"id":"2503.08085","title":"PRISM: Privacy-Preserving Improved Stochastic Masking for Federated Generative Models","created":"2025-03-11","cited_by_count":3},{"id":"2105.11611","title":"KnowSR: Knowledge Sharing among Homogeneous Agents in Multi-agent Reinforcement Learning","created":"2021-05-25","cited_by_count":2},{"id":"2406.09835","title":"I Know How: Combining Prior Policies to Solve New Tasks","created":"2024-06-14","cited_by_count":2},{"id":"2503.02437","title":"Decentralized Reinforcement Learning for Multi-Agent Multi-Resource Allocation via Dynamic Cluster Agreements","created":"2025-03-04","cited_by_count":2},{"id":"2307.05834","title":"Scaling Distributed Multi-task Reinforcement Learning with Experience Sharing","created":"2023-07-11","cited_by_count":1},{"id":"2403.06535","title":"Decentralized and Lifelong-Adaptive Multi-Agent Collaborative Learning","created":"2024-03-11","cited_by_count":1},{"id":"2410.00074","title":"Collaborative Knowledge Distillation via a Learning-by-Education Node Community","created":"2024-09-30","cited_by_count":1}],"next_cursor":null}