{"list":"other","total":60,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"2004.07219","title":"D4RL: Datasets for Deep Data-Driven Reinforcement Learning","created":"2020-04-15","cited_by_count":1427},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"2002.12327","title":"A Primer in BERTology: What we know about how BERT works","created":"2020-02-27","cited_by_count":815},{"id":"1802.06070","title":"Diversity is All You Need: Learning Skills without a Reward Function","created":"2018-02-16","cited_by_count":752},{"id":"2007.03898","title":"NVAE: A Deep Hierarchical Variational Autoencoder","created":"2020-07-08","cited_by_count":637},{"id":"1903.01973","title":"Learning Latent Plans from Play","created":"2019-03-05","cited_by_count":316},{"id":"1907.01657","title":"Dynamics-Aware Unsupervised Discovery of Skills","created":"2019-07-02","cited_by_count":313},{"id":"1909.07528","title":"Emergent Tool Use From Multi-Agent Autocurricula","created":"2019-09-17","cited_by_count":313},{"id":"1807.01281","title":"Human-level performance in first-person multiplayer games with population-based deep reinforcement learning","created":"2018-07-03","cited_by_count":264},{"id":"2011.10650","title":"Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images","created":"2020-11-20","cited_by_count":264},{"id":"2009.05041","title":"Understanding the Role of Individual Units in a Deep Neural Network","created":"2020-09-10","cited_by_count":255},{"id":"1910.07969","title":"On Completeness-aware Concept-Based Explanations in Deep Neural Networks","created":"2019-10-17","cited_by_count":239},{"id":"2010.11944","title":"Accelerating Reinforcement Learning with Learned Skill Priors","created":"2020-10-22","cited_by_count":223},{"id":"1611.05148","title":"Variational Deep Embedding: An Unsupervised and Generative Approach to Clustering","created":"2016-11-16","cited_by_count":220},{"id":"1804.02477","title":"Programmatically Interpretable Reinforcement Learning","created":"2018-04-06","cited_by_count":193},{"id":"1903.10145","title":"Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing","created":"2019-03-25","cited_by_count":191},{"id":"2010.13611","title":"OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning","created":"2020-10-26","cited_by_count":166},{"id":"2006.00979","title":"Acme: A Research Framework for Distributed Reinforcement Learning","created":"2020-06-01","cited_by_count":146},{"id":"2011.10024","title":"Parrot: Data-Driven Behavioral Priors for Reinforcement Learning","created":"2020-11-19","cited_by_count":138},{"id":"2010.01523","title":"RODE: Learning Roles to Decompose Multi-Agent Tasks","created":"2020-10-04","cited_by_count":125},{"id":"2111.09259","title":"Acquisition of Chess Knowledge in AlphaZero","created":"2021-11-17","cited_by_count":123},{"id":"1807.10299","title":"Variational Option Discovery Algorithms","created":"2018-07-26","cited_by_count":122},{"id":"2002.03647","title":"Explore, Discover and Learn: Unsupervised Discovery of State-Covering Skills","created":"2020-02-10","cited_by_count":122},{"id":"1710.03748","title":"Emergent Complexity via Multi-Agent Competition","created":"2017-10-10","cited_by_count":120},{"id":"2002.00632","title":"Effective Diversity in Population Based Reinforcement Learning","created":"2020-02-03","cited_by_count":119},{"id":"1705.08841","title":"Multi-Level Variational Autoencoder: Learning Disentangled Representations from Grouped Observations","created":"2017-05-24","cited_by_count":100},{"id":"2008.06693","title":"Explainability in Deep Reinforcement Learning","created":"2020-08-15","cited_by_count":97},{"id":"2102.07475","title":"Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing","created":"2021-02-15","cited_by_count":87},{"id":"2105.12196","title":"From Motor Control to Team Play in Simulated Humanoid Football","created":"2021-05-25","cited_by_count":87},{"id":"2109.13841","title":"Bottom-Up Skill Discovery from Unsegmented Demonstrations for Long-Horizon Robot Manipulation","created":"2021-09-28","cited_by_count":83},{"id":"1602.02658","title":"Graying the black box: Understanding DQNs","created":"2016-02-08","cited_by_count":68},{"id":"1804.02808","title":"Latent Space Policies for Hierarchical Reinforcement Learning","created":"2018-04-09","cited_by_count":67},{"id":"2106.13105","title":"The Option Keyboard: Combining Skills in Reinforcement Learning","created":"2021-06-24","cited_by_count":67},{"id":"1802.04564","title":"Diversity-Driven Exploration Strategy for Deep Reinforcement Learning","created":"2018-02-13","cited_by_count":65},{"id":"1804.03980","title":"Emergent Communication through Negotiation","created":"2018-04-11","cited_by_count":62},{"id":"1902.07151","title":"Emergent Coordination Through Competition","created":"2019-02-19","cited_by_count":57},{"id":"2006.16232","title":"Learning Robot Skills with Temporal Variational Inference","created":"2020-06-29","cited_by_count":54},{"id":"1912.09007","title":"Interestingness Elements for Explainable Reinforcement Learning: Understanding Agents' Capabilities and Limitations","created":"2019-12-19","cited_by_count":50},{"id":"1912.03558","title":"Hierarchical Cooperative Multi-Agent Reinforcement Learning with Skill Discovery","created":"2019-12-07","cited_by_count":43},{"id":"1709.06683","title":"OptionGAN: Learning Joint Reward-Policy Options using Generative Adversarial Inverse Reinforcement Learning","created":"2017-09-20","cited_by_count":40},{"id":"2105.15164","title":"DISSECT: Disentangled Simultaneous Explanations via Concept Traversals","created":"2021-05-31","cited_by_count":37},{"id":"2103.04564","title":"Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization","created":"2021-03-08","cited_by_count":35},{"id":"2012.07827","title":"Relative Variational Intrinsic Control","created":"2020-12-14","cited_by_count":34},{"id":"2111.02767","title":"RLDS: an Ecosystem to Generate, Share and Use Datasets in Reinforcement Learning","created":"2021-11-04","cited_by_count":31},{"id":"1805.10309","title":"Learning Self-Imitating Diverse Policies","created":"2018-05-25","cited_by_count":29},{"id":"2106.14305","title":"Unsupervised Skill Discovery with Bottleneck Option Learning","created":"2021-06-27","cited_by_count":28},{"id":"2112.05062","title":"Learning Transferable Motor Skills with Hierarchical Latent Mixture Policies","created":"2021-12-09","cited_by_count":26},{"id":"2204.02246","title":"Continuously Discovering Novel Strategies via Reward-Switching Policy Optimization","created":"2022-04-04","cited_by_count":23},{"id":"2205.06760","title":"Emergent Bartering Behaviour in Multi-Agent Reinforcement Learning","created":"2022-05-13","cited_by_count":19},{"id":"2101.10276","title":"Emergent Communication under Competition","created":"2021-01-25","cited_by_count":18},{"id":"1912.01160","title":"Neighborhood Cognition Consistent Multi-Agent Reinforcement Learning","created":"2019-12-03","cited_by_count":17},{"id":"1902.00154","title":"Towards Generating Long and Coherent Text with Multi-Level Latent Variable Models","created":"2019-02-01","cited_by_count":11},{"id":"1605.05359","title":"Option Discovery in Hierarchical Reinforcement Learning using Spatio-Temporal Clustering","created":"2016-05-17","cited_by_count":6},{"id":"2202.04675","title":"Bayesian Nonparametrics for Offline Skill Discovery","created":"2022-02-09","cited_by_count":5},{"id":"1811.04324","title":"Diversity-Driven Extensible Hierarchical Reinforcement Learning","created":"2018-11-10","cited_by_count":4},{"id":"1909.04134","title":"Option Encoder: A Framework for Discovering a Policy Basis in Reinforcement Learning","created":"2019-09-09","cited_by_count":3},{"id":"1902.03633","title":"Diverse Exploration via Conjugate Policies for Policy Gradient Methods","created":"2019-02-10","cited_by_count":2}],"next_cursor":null}