Projects per year
Abstract
Constructing robust controllers to perform tasks in large, continually
changing worlds is a difficult problem. A long-lived
agent placed in such a world could be required to perform a
variety of different tasks. For this to be possible, the agent
needs to be able to abstract its experiences in a reusable way.
This paper addresses the problem of online multitask decision
making in such complex worlds, with inherent incompleteness
in models of change. A fully general version of
this problem is intractable but many interesting domains are
rendered manageable by the fact that all instances of tasks
may be described using a finite set of qualitatively meaningful
contexts. We suggest an approach to solving the multitask
problem through decomposing the domain into a set of capabilities
based on these local contexts. Capabilities resemble
the options of hierarchical reinforcement learning, but provide
robust behaviours capable of achieving some subgoal
with the associated guarantee of achieving at least a particular
aspiration level of performance. This enables using these
policies within a planning framework, and they become a
level of abstraction which factorises an otherwise large domain
into task-independent sub-problems, with well-defined
interfaces between the perception, control and planning problems.
This is demonstrated in a stochastic navigation example,
where an agent reaches different goals in different world
instances without relearning.
Original language | English |
---|---|
Title of host publication | AAAI Spring Symposium: Designing Intelligent Robots |
Publisher | AAAI Press |
Number of pages | 6 |
Publication status | Published - 2012 |
Publication series
Name | AAAI Technical Report: Designing Intelligent Robots: Reintegrating AI |
---|---|
Number | SS-12-02 |
Fingerprint
Dive into the research topics of 'A Multitask Representation Using Reusable Local Policy Templates.'. Together they form a unique fingerprint.Projects
- 2 Finished
-
Smart Society - Hybrid and Diversity-Aware Collective Adaptive Systems: When People Meet Machines to Build a Smarter Society (OTHER)
Rovatsos, M., Anderson, S., Ramamoorthy, R. & Robertson, D.
1/01/13 → 31/12/16
Project: Research
-
TOMSY: Topology Based Motion Synthesis for Dextrous Manipulation
Vijayakumar, S., Komura, T. & Ramamoorthy, R.
1/04/11 → 31/03/14
Project: Research