Transferring Agent Behaviors from Videos via Motion GANs
arXiv:1711.07676
Abstract
A major bottleneck for developing general reinforcement learning agents is determining rewards that will yield desirable behaviors under various circumstances. We introduce a general mechanism for automatically specifying meaningful behaviors from raw pixels. In particular, we train a generative adversarial network to produce short sub-goals represented through motion templates. We demonstrate that this approach generates visually meaningful behaviors in unknown environments with novel agents and describe how these motions can be used to train reinforcement learning agents.
arXiv commentDeep Reinforcement Learning Symposium, NIPS 2017
References in corpus (8)
- Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation
- Generative Adversarial Imitation Learning
- Unsupervised Learning for Physical Interaction through Video Prediction
- Towards Vision-Based Deep Reinforcement Learning for Robotic Motion Control
- Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World
- Time-Contrastive Networks: Self-Supervised Learning from Video
- Perceptual Reward Functions
- Discover and Learn New Objects from Documentaries