 Deep Adversarial Reinforcement Learning for Object DisentanglingIEEE/RJS International Conference on Intelligent RObots and Systems (IROS), 2020 |
 Estimating Q(s,s') with Deep Deterministic Dynamics GradientsInternational Conference on Machine Learning (ICML), 2020 |
 Language as a Cognitive Tool to Imagine Goals in Curiosity-Driven
ExplorationNeural Information Processing Systems (NeurIPS), 2020 |
 Learning to Prove Theorems by Learning to Generate TheoremsNeural Information Processing Systems (NeurIPS), 2020 |
 |
 |
 Towards Practical Multi-Object Manipulation using Relational
Reinforcement LearningIEEE International Conference on Robotics and Automation (ICRA), 2019 |
 How Should an Agent Practice?AAAI Conference on Artificial Intelligence (AAAI), 2019 |
 Unsupervised Curricula for Visual Meta-Reinforcement LearningNeural Information Processing Systems (NeurIPS), 2019 |
 Planning with Goal-Conditioned PoliciesNeural Information Processing Systems (NeurIPS), 2019 |
 Keeping Your Distance: Solving Sparse Reward Tasks Using Self-Balancing
Shaped RewardsNeural Information Processing Systems (NeurIPS), 2019 |
 Learning from Trajectories via Subgoal DiscoveryNeural Information Processing Systems (NeurIPS), 2019 |
 Policy Continuation with Hindsight Inverse DynamicsNeural Information Processing Systems (NeurIPS), 2019 |
 Adaptive Curriculum Generation from Demonstrations for Sim-to-Real
Visuomotor ControlIEEE International Conference on Robotics and Automation (ICRA), 2019 |
 Reinforcement Learning for Robotic Manipulation using Simulated
Locomotion DemonstrationsMachine-mediated learning (ML), 2019 |
 Teacher algorithms for curriculum learning of Deep RL in continuously
parameterized environmentsConference on Robot Learning (CoRL), 2019 |
 Self-Paced Contextual Reinforcement LearningConference on Robot Learning (CoRL), 2019 |
 Discovery of Useful Questions as Auxiliary TasksNeural Information Processing Systems (NeurIPS), 2019 |
 Hindsight Trust Region Policy OptimizationInternational Joint Conference on Artificial Intelligence (IJCAI), 2019 |
 Dynamical Distance Learning for Semi-Supervised and Unsupervised Skill
DiscoveryInternational Conference on Learning Representations (ICLR), 2019 |
 |
 Learning to Plan Hierarchically from CurriculumIEEE Robotics and Automation Letters (RA-L), 2019 |
 Goal-conditioned Imitation LearningNeural Information Processing Systems (NeurIPS), 2019 |
 Sub-policy Adaptation for Hierarchical Reinforcement LearningInternational Conference on Learning Representations (ICLR), 2019 |
 Curriculum Learning for Cumulative Return MaximizationInternational Joint Conference on Artificial Intelligence (IJCAI), 2019 |
 Exploration via Hindsight Goal GenerationNeural Information Processing Systems (NeurIPS), 2019 |
 Autonomous Reinforcement Learning of Multiple Interrelated TasksJoint IEEE International Conference on Development and Learning and on Epigenetic Robotics (ICDL-EpiRob), 2019 |
 Maximum Entropy-Regularized Multi-Goal Reinforcement LearningInternational Conference on Machine Learning (ICML), 2019 |
 MaMiC: Macro and Micro Curriculum for Robotic Reinforcement LearningAdaptive Agents and Multi-Agent Systems (AAMAS), 2019 |
 |
 Competitive Experience ReplayInternational Conference on Learning Representations (ICLR), 2019 |
 Addressing Sample Complexity in Visual Tasks Using HER and Hallucinatory
GANsNeural Information Processing Systems (NeurIPS), 2019 |
 An Optimization Framework for Task Sequencing in Curriculum LearningJoint IEEE International Conference on Development and Learning and on Epigenetic Robotics (ICDL-EpiRob), 2019 |
