Robotics

Offline Reinforcement Learning at Multiple Frequencies CoRL 2022 Offline Reinforcement Learning for Visual Navigation CoRL 2022 Online Inverse Reinforcement Learning with Learned Observation Model CoRL 2022 On Optimizing Interventions in Shared Autonomy AAAI 2022 On-Robot Learning With Equivariant Models CoRL 2022 On the Effectiveness of Iterative Learning Control L4DC 2022 Open-Ended Reinforcement Learning with Neural Reward Functions NeurIPS 2022 Optimal Pointing Sequences in Spacecraft Formation Flying Using Online Planning with Resource Constraints L4DC 2022 Optimistic Initialization for Exploration in Continuous Control AAAI 2022 Out-of-Dynamics Imitation Learning from Multimodal Demonstrations CoRL 2022 PaCo: Parameter-Compositional Multi-task Reinforcement Learning NeurIPS 2022 PALMER: Perception - Action Loop with Memory for Long-Horizon Planning NeurIPS 2022 PAnDR: Fast Adaptation to New Environments from Offline Experiences via Decoupling Policy and Environment Representations IJCAI 2022 Phasic Self-Imitative Reduction for Sparse-Reward Goal-Conditioned Reinforcement Learning ICML 2022 PI-QT-Opt: Predictive Information Improves Multi-Task Robotic Reinforcement Learning at Scale CoRL 2022 Planning with Diffusion for Flexible Behavior Synthesis ICML 2022 PLATO: Predicting Latent Affordances Through Object-Centric Play CoRL 2022 Play it by Ear: Learning Skills amidst Occlusion through Audio-Visual Imitation Learning RSS 2022 PONI: Potential Functions for ObjectGoal Navigation With Interaction-Free Learning CVPR 2022 PowerGym: A Reinforcement Learning Environment for Volt-Var Control in Power Distribution Systems L4DC 2022 Programmatic Reward Design by Example AAAI 2022 PropEM-L: Radio Propagation Environment Modeling and Learning for Communication-Aware Multi-Robot Exploration RSS 2022 Provable Defense against Backdoor Policies in Reinforcement Learning NeurIPS 2022 Provably Feedback-Efficient Reinforcement Learning via Active Reward Learning NeurIPS 2022 Provably sample-efficient RL with side information about latent dynamics NeurIPS 2022