Unifying Count-Based Exploration and Intrinsic Motivation

We consider an agent's uncertainty about its environment and the problem of generalizing this uncertainty across observations. Specifically, we focus on the problem of exploration in non-tabular reinforcement learning. Drawing inspiration from the intrinsic motivation literature, we use density models to measure uncertainty, and propose a novel algorithm for deriving a pseudo-count from an arbitrary density model. This technique enables us to generalize count-based exploration algorithms to the non-tabular case. We apply our ideas to Atari 2600 games, providing sensible pseudo-counts from raw pixels. We transform these pseudo-counts into intrinsic rewards and obtain significantly improved exploration in a number of hard games, including the infamously difficult Montezuma's Revenge.

PDF Abstract NeurIPS 2016 PDF NeurIPS 2016 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Atari Games Atari 2600 Freeway A3C-CTS Score 30.48 # 32
Atari Games Atari 2600 Gravitar A3C-CTS Score 238.68 # 49
Atari Games Atari 2600 Montezuma's Revenge DDQN-PC Score 3459 # 10
Atari Games Atari 2600 Montezuma's Revenge A3C-CTS Score 273.7 # 23
Atari Games Atari 2600 Private Eye A3C-CTS Score 99.32 # 46
Atari Games Atari 2600 Venture A3C-CTS Score 0.0 # 49


No methods listed for this paper. Add relevant methods here