{"list":"other","total":64,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1606.09282","title":"Learning without Forgetting","created":"2016-06-29","cited_by_count":2496},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"1606.01540","title":"OpenAI Gym","created":"2016-06-05","cited_by_count":1736},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"1710.02298","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","created":"2017-10-06","cited_by_count":786},{"id":"1810.11910","title":"Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference","created":"2018-10-29","cited_by_count":521},{"id":"1807.03765","title":"Is Q-learning Provably Efficient?","created":"2018-07-10","cited_by_count":487},{"id":"1912.01588","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","created":"2019-12-03","cited_by_count":483},{"id":"1609.05140","title":"The Option-Critic Architecture","created":"2016-09-16","cited_by_count":448},{"id":"2012.15085","title":"Is Pessimism Provably Efficient for Offline RL?","created":"2020-12-30","cited_by_count":364},{"id":"1904.12901","title":"Challenges of Real-World Reinforcement Learning","created":"2019-04-29","cited_by_count":291},{"id":"2012.13490","title":"Towards Continual Reinforcement Learning: A Review and Perspectives","created":"2020-12-25","cited_by_count":274},{"id":"1802.07740","title":"Machine Theory of Mind","created":"2018-02-21","cited_by_count":226},{"id":"1709.04326","title":"Learning with Opponent-Learning Awareness","created":"2017-09-13","cited_by_count":222},{"id":"2006.02419","title":"Emergent Multi-Agent Communication in the Deep Learning Era","created":"2020-06-03","cited_by_count":170},{"id":"2305.19452","title":"Bigger, Better, Faster: Human-level Atari with human-level efficiency","created":"2023-05-30","cited_by_count":147},{"id":"1711.01239","title":"Routing Networks: Adaptive Selection of Non-linear Functions for Multi-Task Learning","created":"2017-11-03","cited_by_count":126},{"id":"2011.06619","title":"Learning Latent Representations to Influence Multi-Agent Interaction","created":"2020-11-12","cited_by_count":93},{"id":"1804.03720","title":"Gotta Learn Fast: A New Benchmark for Generalization in RL","created":"2018-04-10","cited_by_count":59},{"id":"2010.02966","title":"Reinforcement Learning with Random Delays","created":"2020-10-06","cited_by_count":59},{"id":"1904.12774","title":"Routing Networks and the Challenges of Modular and Compositional Computation","created":"2019-04-29","cited_by_count":50},{"id":"1802.05098","title":"DiCE: The Infinitely Differentiable Monte-Carlo Estimator","created":"2018-02-14","cited_by_count":46},{"id":"1805.07830","title":"Learning to Teach in Cooperative Multiagent Reinforcement Learning","created":"2018-05-20","cited_by_count":45},{"id":"2011.00382","title":"A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning","created":"2020-10-31","cited_by_count":41},{"id":"1911.04448","title":"Real-Time Reinforcement Learning","created":"2019-11-11","cited_by_count":40},{"id":"1807.04640","title":"Automatically Composing Representation Transformations as a Means for Generalization","created":"2018-07-12","cited_by_count":35},{"id":"1711.06761","title":"Scalable Recollections for Continual Lifelong Learning","created":"2017-11-17","cited_by_count":33},{"id":"1810.11583","title":"Learning Abstract Options","created":"2018-10-27","cited_by_count":31},{"id":"2101.11992","title":"Acting in Delayed Environments with Non-Stationary Markov Policies","created":"2021-01-28","cited_by_count":31},{"id":"2203.12759","title":"Asynchronous Reinforcement Learning for Real-Time Control of Physical Robots","created":"2022-03-23","cited_by_count":22},{"id":"2108.07555","title":"Revisiting State Augmentation methods for Reinforcement Learning with Stochastic Delays","created":"2021-08-17","cited_by_count":21},{"id":"1808.01813","title":"Regret Bounds for Reinforcement Learning via Markov Chain Concentration","created":"2018-08-06","cited_by_count":19},{"id":"2108.01005","title":"Sequoia: A Software Framework to Unify Continual Learning Research","created":"2021-08-02","cited_by_count":19},{"id":"2203.03535","title":"Influencing Long-Term Behavior in Multiagent Reinforcement Learning","created":"2022-03-07","cited_by_count":18},{"id":"2406.04879","title":"A Deep Dive into the Trade-Offs of Parameter-Efficient Preference Alignment Techniques","created":"2024-06-07","cited_by_count":16},{"id":"2011.07715","title":"Blind Decision Making: Reinforcement Learning with Delayed Observations","created":"2020-11-16","cited_by_count":15},{"id":"2112.07066","title":"Continual Learning In Environments With Polynomial Mixing Times","created":"2021-12-13","cited_by_count":14},{"id":"2201.08484","title":"Iterated Reasoning with Mutual Information in Cooperative and Byzantine Decentralized Teaming","created":"2022-01-20","cited_by_count":14},{"id":"2212.04407","title":"Dynamic Decision Frequency with Continuous Options","created":"2022-12-06","cited_by_count":13},{"id":"2403.12309","title":"Reinforcement Learning from Delayed Observations via World Models","created":"2024-03-18","cited_by_count":13},{"id":"1802.06139","title":"Reactive Reinforcement Learning in Asynchronous Environments","created":"2018-02-16","cited_by_count":12},{"id":"1904.09330","title":"Continual Learning with Self-Organizing Maps","created":"2019-04-19","cited_by_count":10},{"id":"2403.12805","title":"Contextual Moral Value Alignment Through Context-Based Aggregation","created":"2024-03-19","cited_by_count":10},{"id":"2004.13242","title":"Efficient Black-Box Planning Using Macro-Actions with Focused Effects","created":"2020-04-28","cited_by_count":9},{"id":"1912.13408","title":"On the Role of Weight Sharing During Deep Option Learning","created":"2019-12-31","cited_by_count":8},{"id":"2006.09437","title":"A Study of Compositional Generalization in Neural Models","created":"2020-06-16","cited_by_count":8},{"id":"2109.09876","title":"Context-Specific Representation Abstraction for Deep Option Learning","created":"2021-09-20","cited_by_count":8},{"id":"1910.12453","title":"Asynchronous Methods for Model-Based Reinforcement Learning","created":"2019-10-28","cited_by_count":7},{"id":"1704.03617","title":"Representation Stability as a Regularizer for Improved Text Analytics Transfer Learning","created":"2017-04-12","cited_by_count":6},{"id":"2001.10474","title":"Coagent Networks Revisited","created":"2020-01-28","cited_by_count":6},{"id":"2010.04646","title":"Deep RL With Information Constrained Policies: Generalization in Continuous Control","created":"2020-10-09","cited_by_count":6},{"id":"2411.06824","title":"Combining Domain and Alignment Vectors to Achieve Better Knowledge-Safety Trade-offs in LLMs","created":"2024-11-11","cited_by_count":6},{"id":"2210.16175","title":"Game-Theoretical Perspectives on Active Equilibria: A Preferred Solution Concept over Nash Equilibria","created":"2022-10-28","cited_by_count":5},{"id":"2303.17508","title":"Learning in Factored Domains with Information-Constrained Visual Representations","created":"2023-03-30","cited_by_count":4},{"id":"2305.05760","title":"Reducing the Cost of Cycle-Time Tuning for Real-World Policy Optimization","created":"2023-05-09","cited_by_count":4},{"id":"1507.06667","title":"Alexandria: Extensible Framework for Rapid Exploration of Social Media","created":"2015-07-23","cited_by_count":3},{"id":"2011.11517","title":"Consolidation via Policy Information Regularization in Deep RL for Multi-Agent Games","created":"2020-11-23","cited_by_count":3},{"id":"2204.10374","title":"Learning how to Interact with a Complex Interface using Hierarchical Reinforcement Learning","created":"2022-04-21","cited_by_count":3}],"next_cursor":null}