Autonomous shaping: knowledge transfer in reinforcement learning

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.

• Type: Conference
• Year: 2006
• Where: ICML
• Authors: George Konidaris, Andrew G. Barto
• Keywords: Difficult Tasks, ICML 2006, Later Tasks, Machine Learning, Reinforcement Learning Tasks