Intra-task Curriculum Learning for Faster Reinforcement Learning in Video Games
In this paper we present a new method for improving reinforcement learning training times under the following two assumptions: (1) we know the conditions under which the environment gives reward; and (2) we can control the initial state of the environment at the beginning of a training episode. Our method, called intra-task curriculum learning, presents the different episode starting states to an agent in order of increasing distance to immediate reward.
- 1.Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, vol. 1. MIT Press, Cambridge (1998)Google Scholar
- 3.Pathak, D., et al.: Curiosity-driven exploration by self-supervised prediction. In: ICML (2017)Google Scholar
- 4.Chentanez, N., Barto, A.G., Singh, S.P.: Intrinsically motivated reinforcement learning. In: NIPS, pp. 1281–1288 (2005)Google Scholar
- 5.Dosovitskiy, A., Koltun, V.: Learning to act by predicting the future. In: ICLR (2017)Google Scholar
- 6.Bengio, Y., et al.: Curriculum learning. In: ICML, pp. 41–48 (2009)Google Scholar
- 7.van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double q-learning. In: AAAI (2016)Google Scholar