Autonomous Task Sequencing for Customized Curriculum Design in Reinforcement Learning (2017)
Transfer learning is a method where an agent reuses knowledge learned in a source task to improve learning on a target task. Recent work has shown that transfer learning can be extended to the idea of curriculum learning, where the agent incrementally accumulates knowledge over a sequence of tasks (i.e. a curriculum). In most existing work, such curricula have been constructed manually. Furthermore, they are fixed ahead of time, and do not adapt to the progress or abilities of the agent. In this paper, we formulate the design of a curriculum as a Markov Decision Process, which directly models the accumulation of knowledge as an agent interacts with tasks, and propose a method that approximates an execution of an optimal policy in this MDP to produce an agent-specific curriculum. We use our approach to automatically sequence tasks for 3 agents with varying sensing and action capabilities in an experimental domain, and show that our method produces curricula customized for each agent that improve performance relative to learning from scratch or using a different agent's curriculum.
In Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI), Melbourne, Australia, August 2017.

Slides (PDF)
Sanmit Narvekar Ph.D. Student sanmit [at] cs utexas edu
Jivko Sinapov Postdoctoral Alumni jsinapov [at] cs utexas edu
Peter Stone Faculty pstone [at] cs utexas edu