Imagination-Augmented Agents for Deep Reinforcement Learning

We introduce Imagination-Augmented Agents (I2As), a novel architecture for deep reinforcement learning combining model-free and model-based aspects. In contrast to most existing model-based reinforcement learning and planning methods, which prescribe how a model should be used to arrive at a policy, I2As learn to interpret predictions from a trained environment model to construct implicit plans in arbitrary ways, by using the predictions as additional context in deep policy networks. I2As show improved data efficiency, performance, and robustness to model misspecification compared to several strong baselines.

Authors

• Sébastien Racanière
• Theophane Weber
• David Reichert
• Lars Buesing
• Arthur Guez
• Danilo Jimenez Rezende
• Adrià Puigdomènech Badia Google DeepMind
• Oriol Vinyals
• Nicolas Heess
• Yujia Li
• Razvan Pascanu
• Peter Battaglia
• Demis Hassabis
• David Silver
• Daan Wierstra

Keywords

No keywords are indexed for this paper.