Autonomous shaping: knowledge transfer in reinforcement learning

George Dimitri Konidaris, Andrew G. Barto

Abstract

We introduce the use of learned shaping rewards in reinforcement learning tasks, where an agent uses prior experience on a sequence of tasks to learn a portable predictor that estimates intermediate rewards, resulting in accelerated learning in later tasks that are related but distinct. Such agents can be trained on a sequence of relatively easy tasks in order to develop a more informative measure of reward that can be transferred to improve performance on more difficult tasks without requiring a hand coded shaping function. We use a rod positioning task to show that this significantly improves performance even after a very brief training period.
BibTeX
@inproceedings{konidaris2006autonomous,
  author = {George Dimitri Konidaris and Andrew G. Barto},
  title = {{Autonomous shaping: knowledge transfer in reinforcement learning}},
  booktitle = {International Conference on Machine Learning},
  year = {2006},
  doi = {10.1145/1143844.1143906},
}

Loading related content...

Figure