What Would You Do? Acting by Learning to Predict
arXiv:1703.02658
Abstract
We propose to learn tasks directly from visual demonstrations by learning to predict the outcome of human and robot actions on an environment. We enable a robot to physically perform a human demonstrated task without knowledge of the thought processes or actions of the human, only their visually observable state transitions. We evaluate our approach on two table-top, object manipulation tasks and demonstrate generalisation to previously unseen states. Our approach reduces the priors required to implement a robot task learning system compared with the existing approaches of Learning from Demonstration, Reinforcement Learning and Inverse Reinforcement Learning.
Submitted to International Conference on Intelligent Robots and Systems (IROS 2017)
References in corpus (8)
- Unsupervised Learning of Video Representations using LSTMs
- Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization
- Deep Reinforcement Learning: An Overview
- Action-Conditional Video Prediction using Deep Networks in Atari Games
- Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning
- Unsupervised Learning for Physical Interaction through Video Prediction
- Spatio-temporal video autoencoder with differentiable memory
- Learning Through Time in the Thalamocortical Loops