Published inTDS ArchiveThe Power of Offline Reinforcement LearningRL algorithms that could potentially scale to real-world problemsNov 1, 20201Nov 1, 20201
Published inTDS ArchiveGeneralization in Deep Reinforcement LearningLearning policies that generalize beyond their training environmentNov 21, 20191Nov 21, 20191
Published inTDS ArchiveModel Based Policy OptimizationReviewing recent advances in model-based reinforcement learning.Aug 1, 2019Aug 1, 2019
Published inTDS ArchiveReinforcement Learning for Real-World RoboticsIdeas from the literature on RL for real-world robot controlMay 3, 20194May 3, 20194
Published inTDS ArchiveReinforcement Learning for Combinatorial OptimizationLearning strategies to tackle difficult optimization problems using Deep Reinforcement Learning and Graph Neural Networks.Apr 6, 20192Apr 6, 20192
Published inTDS ArchiveRobotic Control with Graph NetworksExploiting relational inductive bias to improve generalization and controlMar 16, 20193Mar 16, 20193
Published inTDS ArchiveLearning to Plan with Value Iteration NetworksNeural Networks that can learn to mimic planning algorithmsMar 5, 20191Mar 5, 20191
Published inTDS ArchiveReinforcement Learning Using a Single DemonstrationLearning from DemonstrationFeb 16, 2019Feb 16, 2019
Published inTDS ArchiveReinforcement Learning with Hindsight Experience ReplaySparse and Binary RewardsJan 31, 20192Jan 31, 20192
Published inTDS ArchiveReinforcement Learning with Exploration by Random Network DistillationEver since the seminal DQN work by DeepMind in 2013, in which an agent successfully learned to play Atari games at a level that is higher…Jan 24, 20193Jan 24, 20193
