Intelligent animals devote much time and energy to exploring and obtaining information, but the underlying mechanisms are poorly understood. We review recent developments on this …
Reinforcement learning allows solving complex tasks, however, the learning tends to be task- specific and the sample efficiency remains a challenge. We present Plan2Explore, a self …
We introduce an exploration bonus for deep reinforcement learning methods that is easy to implement and adds minimal overhead to the computation performed. The bonus is the error …
Sequential decision making, commonly formalized as Markov Decision Process (MDP) optimization, is an important challenge in artificial intelligence. Two key approaches to this …
Reinforcement learning algorithms rely on carefully engineering environment rewards that are extrinsic to the agent. However, annotating each environment with hand-designed …
In many real-world scenarios, rewards extrinsic to the agent are extremely sparse, or absent altogether. In such cases, curiosity can serve as an intrinsic reward signal to enable the …
Efficient exploration is a long-standing problem in sensorimotor learning. Major advances have been demonstrated in noise-free, non-stochastic domains such as video games and …
We consider an agent's uncertainty about its environment and the problem of generalizing this uncertainty across states. Specifically, we focus on the problem of exploration in non …
G Ostrovski, MG Bellemare, A Oord… - … on machine learning, 2017 - proceedings.mlr.press
Abstract Bellemare et al.(2016) introduced the notion of a pseudo-count, derived from a density model, to generalize count-based exploration to non-tabular reinforcement learning …