Online Multi-Task Gradient Temporal-Difference Learning


  • Vishnu Sreenivasan University of Pennsylvania
  • Haitham Bou Ammar University of Pennsylvania
  • Eric Eaton University of Pennsylvania



online multi-task learning, lifelong learning, reinforcement learning, gradient temporal-difference learning


We develop an online multi-task formulation of model-based gradient temporal-difference (GTD) reinforcement learning. Our approach enables an autonomous RL agent to accumulate knowledge over its lifetime and efficiently share this knowledge between tasks to accelerate learning. Rather than learning a policy for a reinforcement learning task tabula rasa, as in standard GTD, our approach rapidly learns a high performance policy by building upon the agent's previously learned knowledge. Our preliminary results on controlling different mountain car tasks demonstrates that GTD-ELLA significantly improves learning over standard GTD(0).




How to Cite

Sreenivasan, V., Bou Ammar, H., & Eaton, E. (2014). Online Multi-Task Gradient Temporal-Difference Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 28(1).