Timezone: »

Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement Learning
Sam Lobel · Akhil Bagaria · George Konidaris

Thu Jul 27 01:30 PM -- 03:00 PM (PDT) @ Exhibit Hall 1 #311

We propose a new method for count-based exploration in high-dimensional state spaces. Unlike previous work which relies on density models, we show that counts can be derived by averaging samples from the Rademacher distribution (or coin flips). This insight is used to set up a simple supervised learning objective which, when optimized, yields a state's visitation count. We show that our method is significantly more effective at deducing ground-truth visitation counts than previous work; when used as an exploration bonus for a model-free reinforcement learning algorithm, it outperforms existing approaches on most of 9 challenging exploration tasks, including the Atari game Montezuma's Revenge.

Author Information

Sam Lobel (Brown University)
Akhil Bagaria (Brown University)
George Konidaris (Brown)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors