#sequential
11 notes
- Hindsight Planner
- Robotic Table Wiping via Reinforcement Learning and Whole-body Trajetory Optimization
- Goal-Conditioned Reinforcement Learning with Imagined Subgoals
- Maximum Entropy Gain Exploration for Long Horizon Multi-goal Reinforcement Learning
- Skew-Fit: State-Covering Self-Supervised Reinforcement Learning
- Unsupervised Control Through Non-Parameteric Discriminative Rewards
- Planning to Practice: Efficient Online Fine-Tuning by Composing Goals in Latent Space
- Near-Optimal Representation Leanring for Hierarchical Reinforcement Learning
- Solving Compositional Reinforcement Learning Problems via Task Reduction
- Multi-Task Learning with Sequence-Conditioned Transporter Networks
- Meta Reinforcement Learning with Aotonomous Inference of Subtask Dependencies