Learning Multi-Stage Tasks with One Demonstration via Self-Replay
arXiv:2111.07447
Abstract
In this work, we introduce a novel method to learn everyday-like multi-stage tasks from a single human demonstration, without requiring any prior object knowledge. Inspired by the recent Coarse-to-Fine Imitation Learning method, we model imitation learning as a learned object reaching phase followed by an open-loop replay of the demonstrator's actions. We build upon this for multi-stage tasks where, following the human demonstration, the robot can autonomously collect image data for the entire multi-stage task, by reaching the next object in the sequence and then replaying the demonstration, and then repeating in a loop for all stages of the task. We evaluate with real-world experiments on a set of everyday-like multi-stage tasks, which we show that our method can solve from a single demonstration. Videos and supplementary material can be found at https://www.robot-learning.uk/self-replay.
arXiv commentPublished at the 5th Conference on Robot Learning (CoRL) 2021
References in corpus (11)
- Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards
- One-Shot Visual Imitation Learning via Meta-Learning
- Learning by Playing - Solving Sparse Reward Tasks from Scratch
- One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning
- DART: Noise Injection for Robust Imitation Learning
- One-Shot Hierarchical Imitation Learning of Compound Visuomotor Tasks
- Learning Latent Plans from Play
- Learning Visual Robotic Control Efficiently with Contrastive Pre-training and Data Augmentation
- Modeling Long-horizon Tasks as Sequential Interaction Landscapes
- Continuous Relaxation of Symbolic Planner for One-Shot Imitation Learning
- SAFARI: Safe and Active Robot Imitation Learning with Imagination