Sample-Efficient Model-based Actor-Critic for an Interactive Dialogue Task

no code implementations • 28 Apr 2020 • Katya Kudashkina, Valliappa Chockalingam, Graham W. Taylor, Michael Bowling

Human-computer interactive systems that rely on machine learning are becoming paramount to the lives of millions of people who use digital assistants on a daily basis.

Model-based Reinforcement Learning

Neural Heterogeneous Scheduler

no code implementations • 9 Jun 2019 • Tegg Taekyong Sung, Valliappa Chockalingam, Alex Yahja, Bo Ryu

Access to parallel and distributed computation has enabled researchers and developers to improve algorithms and performance in many applications.

Decision Making reinforcement-learning +2

Interactions between Representation Learning and Supervision

no code implementations • 25 Mar 2019 • Valliappa Chockalingam

However, representation learning is often also used as an implicit step in supervised learning (SL) or reinforcement learning (RL) problems.

Continual Learning Dimensionality Reduction +3

Control of Memory, Active Perception, and Action in Minecraft

no code implementations • 30 May 2016 • Junhyuk Oh, Valliappa Chockalingam, Satinder Singh, Honglak Lee

In this paper, we introduce a new set of reinforcement learning (RL) tasks in Minecraft (a flexible 3D world).

reinforcement-learning Reinforcement Learning (RL)