Quantizing Behavioral Heterogeneity Jon Beckham 11/21/02.

Slides:



Advertisements
Similar presentations
Linear Regression.
Advertisements

Lecture (11,12) Parameter Estimation of PDF and Fitting a Distribution Function.
1-1 Copyright © 2015, 2010, 2007 Pearson Education, Inc. Chapter 21, Slide 1 Chapter 21 Comparing Two Proportions.
N.D.GagunashviliUniversity of Akureyri, Iceland Pearson´s χ 2 Test Modifications for Comparison of Unweighted and Weighted Histograms and Two Weighted.
Theoretical Program Checking Greg Bronevetsky. Background The field of Program Checking is about 13 years old. Pioneered by Manuel Blum, Hal Wasserman,
COMMUNICATION IN MULTIROBOT TEAMS - BARATH CHRISTOPHER PETIT.
Correlation and Autocorrelation
Reinforcement Learning Rafy Michaeli Assaf Naor Supervisor: Yaakov Engel Visit project’s home page at: FOR.
Evaluating Hypotheses
Motor Schema Based Navigation for a Mobile Robot: An Approach to Programming by Behavior Ronald C. Arkin Reviewed By: Chris Miles.
A Probabilistic Approach to Collaborative Multi-robot Localization Dieter Fox, Wolfram Burgard, Hannes Kruppa, Sebastin Thrun Presented by Rajkumar Parthasarathy.
ECE 776 Information Theory Capacity of Fading Channels with Channel Side Information Andrea J. Goldsmith and Pravin P. Varaiya, Professor Name: Dr. Osvaldo.
8. ANALYSIS OF VARIANCE 8.1 Elements of a Designed Experiment
Inferences About Process Quality
The Neymann-Pearson Lemma Suppose that the data x 1, …, x n has joint density function f(x 1, …, x n ;  ) where  is either  1 or  2. Let g(x 1, …,
CS Reinforcement Learning1 Reinforcement Learning Variation on Supervised Learning Exact target outputs are not given Some variation of reward is.
Fluid Mechanics and Fluid Dynamics
Data Selection In Ad-Hoc Wireless Sensor Networks Olawoye Oyeyele 11/24/2003.
METU Informatics Institute Min 720 Pattern Classification with Bio-Medical Applications PART 2: Statistical Pattern Classification: Optimal Classification.
AM Recitation 2/10/11.
Statistics 11 Hypothesis Testing Discover the relationships that exist between events/things Accomplished by: Asking questions Getting answers In accord.
HAWKES LEARNING SYSTEMS math courseware specialists Copyright © 2010 by Hawkes Learning Systems/Quant Systems, Inc. All rights reserved. Chapter 14 Analysis.
Correlation and Linear Regression
Self-Organizing Agents for Grid Load Balancing Junwei Cao Fifth IEEE/ACM International Workshop on Grid Computing (GRID'04)
Hypothesis Testing II The Two-Sample Case.
1 STATISTICAL HYPOTHESES AND THEIR VERIFICATION Kazimieras Pukėnas.
QNT 531 Advanced Problems in Statistics and Research Methods
Machine Learning1 Machine Learning: Summary Greg Grudic CSCI-4830.
1 Techniques to control noise and fading l Noise and fading are the primary sources of distortion in communication channels l Techniques to reduce noise.
Comparing Two Proportions
Random Sampling, Point Estimation and Maximum Likelihood.
ECE 8443 – Pattern Recognition LECTURE 03: GAUSSIAN CLASSIFIERS Objectives: Normal Distributions Whitening Transformations Linear Discriminants Resources.
Estimating parameters in a statistical model Likelihood and Maximum likelihood estimation Bayesian point estimates Maximum a posteriori point.
Sullivan – Fundamentals of Statistics – 2 nd Edition – Chapter 11 Section 1 – Slide 1 of 34 Chapter 11 Section 1 Random Variables.
Texture. Texture is an innate property of all surfaces (clouds, trees, bricks, hair etc…). It refers to visual patterns of homogeneity and does not result.
A Clustering Algorithm based on Graph Connectivity Balakrishna Thiagarajan Computer Science and Engineering State University of New York at Buffalo.
CS 4630: Intelligent Robotics and Perception Case Study: Motor Schema-based Design Chapter 5 Tucker Balch.
Chapter 1 Introduction to Statistics. Statistical Methods Were developed to serve a purpose Were developed to serve a purpose The purpose for each statistical.
Examining Relationships in Quantitative Research
1 Chapter 6 Estimates and Sample Sizes 6-1 Estimating a Population Mean: Large Samples / σ Known 6-2 Estimating a Population Mean: Small Samples / σ Unknown.
PPA 415 – Research Methods in Public Administration Lecture 7 – Analysis of Variance.
Chapter Seventeen. Figure 17.1 Relationship of Hypothesis Testing Related to Differences to the Previous Chapter and the Marketing Research Process Focus.
Chapter 2: Getting to Know Your Data
Chapter 12 Introduction to Analysis of Variance PowerPoint Lecture Slides Essentials of Statistics for the Behavioral Sciences Eighth Edition by Frederick.
The Restricted Matched Filter for Distributed Detection Charles Sestok and Alan Oppenheim MIT DARPA SensIT PI Meeting Jan. 16, 2002.
Two-Way (Independent) ANOVA. PSYC 6130A, PROF. J. ELDER 2 Two-Way ANOVA “Two-Way” means groups are defined by 2 independent variables. These IVs are typically.
Behavior-based Multirobot Architectures. Why Behavior Based Control for Multi-Robot Teams? Multi-Robot control naturally grew out of single robot control.
Chapter 8: Simple Linear Regression Yang Zhenlin.
Chapter 7 Measuring of data Reliability of measuring instruments The reliability* of instrument is the consistency with which it measures the target attribute.
Lecture 12 Average Rate of Change The Derivative.
Classification Ensemble Methods 1
Sampling Design and Analysis MTH 494 Lecture-21 Ossam Chohan Assistant Professor CIIT Abbottabad.
Basic Concepts of Information Theory A measure of uncertainty. Entropy. 1.
Negotiating Socially Optimal Allocations of Resources U. Endriss, N. Maudet, F. Sadri, and F. Toni Presented by: Marcus Shea.
Path Planning Based on Ant Colony Algorithm and Distributed Local Navigation for Multi-Robot Systems International Conference on Mechatronics and Automation.
Network Partition –Finding modules of the network. Graph Clustering –Partition graphs according to the connectivity. –Nodes within a cluster is highly.
Chapter 4 Variability PowerPoint Lecture Slides Essentials of Statistics for the Behavioral Sciences Seventh Edition by Frederick J Gravetter and Larry.
Copyright © Cengage Learning. All rights reserved. 1 Functions and Limits.
FUNCTIONS AND MODELS 1. The fundamental concepts that we deal with in calculus are functions. This chapter prepares the way for calculus by discussing:
Lecture notes 13: ANOVA (a.k.a. Analysis of Variance)
Machine Learning: Ensemble Methods
Chapter 13 Simple Linear Regression
Modeling and Equation Solving
Comparing Two Proportions
Quantifying Scale and Pattern Lecture 7 February 15, 2005
Basic Statistical Terms
An Introduction to Supervised Learning
Gerald Dyer, Jr., MPH October 20, 2016
Analyzing the Association Between Categorical Variables
Parametric Methods Berlin Chen, 2005 References:
Presentation transcript:

Quantizing Behavioral Heterogeneity Jon Beckham 11/21/02

Papers to Cover  “Measuring Robot Group Diversity”, Balch  “Design & Evaluation of Robust Behavior- Based Controllers”, Goldberg & Mataric  “Symmetry in Markov Decision Processes and its Implications for Single Agent and Multiagent Learning”, Zinkevich & Balch

Quantizing  “Measuring Robot Group Diversity”, Tucker Balch

Purpose  To suggest a standard way of quantitatively measuring diversity. Allows for more accurate, effective analysis. By establishing a standard metric, we can establish a baseline for comparison.

Sources  Simple Social Entropy Adapted from Shannon’s Information Entropy  Behavioral Difference Quantitative measure between different robots.  Hierarchic Social Entropy Combination of the above.

Diversity  To quote Tucker, who quotes Webster… di verse adj 1: differing from one another: unlike. 2: composed of distinct or unlike elements or qualities.

The Discrete Approach  Assume robots are either alike or different; thus assume subsets of identical robots.

Simple Social Entropy  First, some notation: R is a society of N agents, thus R = {r 1, r 2 …r N } C is a classification of R into M subsets c i is an individual subset of C Thus C = {c 1,c 2 …c M } p i is the proportion of agents in the ith subset. Thus, the sum of all p i is 1.

Social Entropy’s Requirements  Continuous (H must be continuous in p i )  Monotonic (H must be monotonically increasing function of M)  Recursive (H must be weighted sum of H of subsets)  H = 0 when system is homogeneous  H is maximized when all p i are equal for given M  Any change to p i to approach greater equality increases H.

Thus…  H(X) = -K∑ M i=1 p i log 2 (p i )  REMEMBER THIS!  Also know that it’s the only equation to satisfy the first three properties (as proven by Shannon in his information entropy work).

Limitations of Simple Social Entropy  Loses data by munging p i and M into single value.  Only works for discrete systems.

What About C?  The classification into subsets… Taxonomy Clustering

More on Taxonomy  Classification at varying levels through a “dendrogram”.

Which Brings Us To Hierarchic Social Entropy  Simple Social Entropy is only a “snapshot” at a particular level of clustering.  To achieve a continuous metric, we use a plot of entropy at all taxonomic levels.  Good because it gives data at all clustering resolutions, putting to rest the clustering issue.

Another Formula  This time for hierarchic social entropy.  S(R) = ∫ 0 ∞ H(R,h)dh

Branching the Taxonomy?  How to get that pretty 2D mapping… Evaluation Chamber? In real world, this requires:  Fixed policies  Mechanically Homogeneous  Policy is reflected directly in overt behavior

Placing Numerical Value on Behavioral Differences  More notation i is a robot’s perceptual state a is the action (behavioral assemblage) selected by a robot’s control system based on the input i. π j is r j ‘s policy; a = π j (i) p i j is the number of times r j has encountered perceptual state I divided by the total number of times all states have been encountered

Simple Behavioral Difference Metric  Continuous D’(r a,r b ) = 1/n ∫ | π a (i) - π b (i) | di  Discrete D’(r a,r b ) = 1/n Σ i | π a (i) - π b (i) | (1/n is normalization factor)

Behavioral Difference  Continuous D’(r a,r b ) = ∫ (p i a + p i b )/2 | π a (i) - π b (i) | di  Discrete D’(r a,r b ) = Σ i (p i a + p i b )/2 | π a (i) - π b (i) |

Definitions  Absolutely behaviorally equivalent Iff two robots select the same behavior in every perceptual state.  ε-equivalent if D(r a,r b ) < ε.  ≡ ε indicates ε-equivalence  A group of robots, R, is ε-homogeneous if for all r a,r b in R, r a ≡ ε r b.

Experiments (briefly)  Multiforaging Behaviors wander stay_near_home acquire_red acquire_blue deliver_red deliver_blue Perceptual Features red_visible blue_visible red_visible_outside_homezone blue_visible_outside_homezone red_in_gripper blue_in_gripper close_to_homezone close_to_red_bin close_to_blue_bin

Methods  Local performance-based reinforcement  Global performance-based reinforcement  Local shaped reinforcement

Results

Summary  Diversity is good in soccer, bad in simple foraging.  Diversity Globally Rewarded, most diverse Locally Rewarded Shaped, least diverse

Conclusions  Diversity as an independent variable  Simple social entropy  Hierarchic social entropy

Problems?  Only deterministic policies  Analysis limited to behavioral diversity

Applying  “Design and Evaluation of Robust Behavior- Based Controllers”, Dani Goldberg and Maja J. Mataric

The Goal  To design multirobot controllers that: Exhibit group-level robustness to robot failures and noise. Are easily modified.

Focus  Simple Foraging

Controllers  One Homogeneous  Two Heterogeneous Pack Caste

Homogeneous Controller  Act concurrently and independently.  Behaviors Avoiding Wandering Puck Detecting Puck Grabbing Homing Boundary Buffer Creeping Home Detector Exiting Reverse Homing Heading

Heterogeneous Pack Controller  Uses temporal arbitration SPST → SPDT  Dominance hierarchy based on capabilities or arbitrary assignment  Only one robot can deliver a puck at a time  Same controller as homogeneous, but uses ‘message passing’ to figure out which robot should deliver first.  Uses communication to determine failed or active.

Heterogeneous Caste Controller  Uses spatial arbitration SPST → DPST  Robots are differentiated into sub-groups or castes  Act concurrently and independently, but in different regions of the task space  May have heterogeneous behavior in addition to spatial heterogeneity  No reliance on communication (Not implemented, but communication could be use to balance caste ratios in case of failure.)

Interference Graphs  Homogeneous  Heterogeneous Pack  Heterogeneous Caste

Analysis Metrics  Inter-robot collisions  Distance traveled by each robot  Time-to-completion

Statistics… Goldberg & Mataric: “We have performed hypothesis tests using Student’s t, 1-factor analysis of variance (ANOVA), and 2-factor ANOVA, in order to verify that the differences between the results of the implementations were in fact statistically significant.” Tucker:

Results

Conclusions  Attempted to apply Balch’s SSE and HSE, but because of vague definitions no clear conclusion could be reached.  Attempted several calculations, but no conclusive relation to performance.  Partly because no best controller.

Flaws  Use of communication in Pack controller, but nowhere else. Allowed pack controller to keep track of state of other robots (working or non-working).