Wish you were here: Hindsight Goal Selection for long-horizon dexterous manipulation

Abstract

Complex sequential tasks in continuous-control settings often require agents to successfully traverse a set of "narrow passages" in their state space. Solving such tasks with a sparse reward in a sample-efficient manner poses a challenge to modern reinforcement learning (RL) due to the associated long-horizon nature of the problem and the lack of sufficient positive signal during learning. Various tools have been applied to address this challenge. When available, large sets of demonstrations can guide agent exploration. Hindsight relabelling on the other hand does not require additional sources of information. However, existing strategies explore based on task-agnostic goal distributions, which can render the solution of long-horizon tasks impractical. In this work, we extend hindsight relabelling mechanisms to guide exploration along task-specific distributions implied by a small set of successful demonstrations. We evaluate the approach on four complex, single and dual arm, robotics manipulation tasks against strong suitable baselines. The method requires far fewer demonstrations to solve all tasks and achieves a significantly higher overall performance as task complexity increases. Finally, we investigate the robustness of the proposed solution with respect to the quality of input representations and the number of demonstrations.

References in corpus (8)

• Solving Rubik's Cube with a Robot Hand
• Rainbow: Combining Improvements in Deep Reinforcement Learning
• Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement
• Self-supervised Learning of Image Embedding for Continuous Control
• Generalized Hindsight for Reinforcement Learning
• Deep Imitation Learning for Bimanual Robotic Manipulation
• Emergent Real-World Robotic Skills via Unsupervised Off-Policy Reinforcement Learning
• An Empirical Investigation of Representation Learning for Imitation