Title: Curious Places
1Curious Places
- A Room that Adapts using Curiosity and Supervised
Learning
Kathryn Merrick, Mary Lou Maher Rob Saunders
October, 2007 Key Centre of Design Computing and
Cognition, University of Sydney
2Overview
- Adaptable, Intelligent Environments
- Curious Supervised Learning
- A Curious, Virtual, Sentient Room
- Limitations and Future Work
3Adaptable, Intelligent Environments
- The computer for the 21st century
- Hundreds of computers per room
- Computers come and go
- (Weiser, 1991)
- Adaptability is important at two levels
- The middleware level
- The behaviour level
4Adaptable Middleware
- Resource management and communication
- Adaptability has been widely considered at this
level - Real time interaction
- Presence services
- Ad hoc networking
Intelligent Room Project
Gaia
BlipSystems
5Adaptable Behaviour
- Adapting behaviour to human activities
- Supervised Learning
- The Neural Network House
- Data mining
- Considered in fixed domains
- How can we achieve adaptive behaviour in response
to changing hardware or software?
6Adaptability by Curiosity and Learning
- Curiosity adapts focus of attention to relevant
learning goals - Learning adapts behaviour to fulfil goals
- Curious reinforcement learning
- Curious supervised learning
MySQL Database
Agent
Projector
Rear projection screen
Curious Information Display
Curious Research Space
PC
Agent
Bluetooth blip nodes
7Supervised Learning
- Learning from examples
- A supervised learning problem P can be
represented formally by - A set S of sensed states
- A set A of actions
- A set X of examples Xi (Si, Ai)
- A policy p S ? A
8Complex, Dynamic Environments
- Contain multiple learning problems
- P P1, P2, P3
- Learning problems in P may change over time
- Addition of new problems
- Removal of obsolete problems
9Modelling Curiosity for Supervised Learning
- Aim to focus attention on states, actions and
examples from a subset of problems - Works by filtering
- Identify potential tasks to
- learn or act upon
- Compute curiosity values
- Arbitrate on what to filter
- High curiosity may trigger
- learning or action
- Low curiosity does not
S(t), X(t)
Curiosity
Observations and events
Task Selection
Curiosity Value
Arbitration
S(t)
X(t)
Learning
Action
10The Curious Supervised Learning Agent
- Past states, examples and actions are stored in
an experience trajectory Y - Experiences may influence curiosity
11A Curious, Virtual, Sentient Room
- A university meeting room in Second Life
- Seminars and Meetings
- Tutorials
- Skype-conferencing
12Virtual Sensors and Effectors
- Floor Sensors
- SmartBoard and Chairs
-
13Meta-Sensors and Meta-Effectors
- Agent does not communicate directly with sensors
and effectors - Agent has a sensor of sensors and an effector
of effectors - BlipSystem provides an up-to-date list of current
sensors and effectors and acts as an intermediary
for communication
14The Curious Room Agent
- Computational model of novelty used for curiosity
- Table-based supervised learning using
associations - Learns accurately but
- Unable to generalise
15Behaviour of the Curious Place
- Avatar enters ? Lights go on
- Avatar sits ? SmartBoard on ? Lights off
16Preliminary Evaluation
- 6 repetitions by human controlled avatars
required for learning - Can adapt to new devices
- Can adapt simple behaviours to form more complex
sequences
17Limitations
- Current prototype is proof-of-concept only, no
significant empirical results yet - Issue of if/when/how to forget behaviours
- Is an interface required for manual editing or
override of learned behaviours?
18Future Work
- Further work on curiosity models
- Design a suite of experiments to test attention
focus in - Environments of increasing complexity
- Dynamic environments
- More complex tasks