Home
Projects
Publications
People
Join the Lab
Contact
Login
Reinforcement Learning
Context-based Online Policy Instantiation for Multiple Tasks and Changing Environments
This paper addresses the problem of online decision making in continually changing and complex environments, with inherent …
Benjamin Rosman
PDF
Cite
Behavioural Domain Knowledge Transfer for Autonomous Agents
An agent continuously performing different tasks in the same domain has the opportunity to learn, over the course of its operational …
Benjamin Rosman
PDF
Cite
Feature Selection for Domain Knowledge Representation through Multitask Learning
Representation learning is a difficult and important problem for autonomous agents. This paper presents an approach to automatic …
Benjamin Rosman
PDF
Cite
Adapting Interaction Environments to Diverse Users through Online Action Set Selection
Interactive interfaces are a common feature of many systems ranging from field robotics to video games. In most applications, these …
MM Hassan Mahmud
,
Benjamin Rosman
,
Subramanian Ramamoorthy
,
Pushmeet Kohli
PDF
Cite
Giving Advice to Agents with Hidden Goals
This paper considers the problem of providing advice to an autonomous agent when neither the behavioural policy nor the goals of that …
Benjamin Rosman
,
Subramanian Ramamoorthy
PDF
Cite
What Good are Actions? Accelerating Learning using Learned Action Priors
The computational complexity of learning in sequential decision problems grows exponentially with the number of actions available to …
Benjamin Rosman
,
Subramanian Ramamoorthy
PDF
Cite
A Multitask Representation using Reusable Local Policy Templates
Constructing robust controllers to perform tasks in large, continually changing worlds is a difficult problem. A long-lived agent …
Benjamin Rosman
,
Subramanian Ramamoorthy
PDF
Cite
Learning Spatial Relationships between Objects
Although a manipulator must interact with objects in terms of their full complexity, it is the qualitative structure of the objects in …
Benjamin Rosman
,
Subramanian Ramamoorthy
PDF
Cite
A Game Theoretic Procedure for Learning Hierarchically Structured Strategies
This paper addresses the problem of acquiring a hierarchically structured robotic skill in a non-stationary environment. This is …
Benjamin Rosman
,
Subramanian Ramamoorthy
PDF
Cite
«
Cite
×