A market-based algorithm is presented which autonomously apportions complex tasks to multiple cooperating agents giving each agent the motivation of improving performance of the whole system. A specific model, called "The Hayek Machine " is proposed and tested on a simulated Blocks World (BW) planning problem. Hayek learns to solve more complex BW problems than any previous learning algorithm. Given intermediate reward and simple features, it has learned to efficiently solve arbitrary BW problems. The Hayek Machine can also be seen as a model of evolutionary economics. 1
|
2138
|
Learning Internal Representations by Error Propagation
– Rumelhart, Hinton, et al.
- 1986
|
|
938
|
Learning from Delayed Rewards
– Watkins
- 1989
|
|
885
|
Learning to Predict by the Methods of Temporal Differences
– Sutton
- 1988
|
|
822
|
Unified Theories of Cognition
– Newell
- 1990
|
|
693
|
Genetic Programming
– Koza
- 1992
|
|
524
|
A framework for representing knowledge
– Minsky
|
|
400
|
Learning to act using Real-Time Dynamic Programming
– Barto, Bradtke, et al.
- 1995
|
|
378
|
Systematic nonlinear planning
– McAllester, Rosenblitt
- 1991
|
|
340
|
An Evolutionary Theory of Economic Change
– Nelson, Winter
- 1984
|
|
317
|
Tragedy of the commons
– Hardin
- 1968
|
|
292
|
The Society of Mind. Simon and
– Minsky
- 1985
|
|
262
|
A Market-Oriented Programming Environment and Its Application to Distributed Multicommodity Flow Problems
– Wellman
- 1993
|
|
244
|
An approach to the synthesis of life
– Ray
- 1992
|
|
230
|
Understanding Natural Language
– Winograd
- 1972
|
|
215
|
Improving elevator performance using reinforcement learning
– Crites, Barto
- 1996
|
|
182
|
The nature of the firm
– Coase
- 1937
|
|
142
|
Models of Bounded Rationality
– Simon
- 1982
|
|
82
|
Pandemonium: A paradigm for learning
– Selfridge
- 1959
|
|
77
|
The Ecology of Computation
– Huberman
- 1988
|
|
77
|
Circuits of the Mind
– VALIANT
- 1994
|
|
76
|
Escaping brittleness: the possibilities of general purpose learning algorithms applied to parallel rule-based systems
– Holland
- 1986
|
|
65
|
PRODIGY4.0: The manual and tutorial
– unknown authors
- 1992
|
|
55
|
Learning to reason
– Khardon, Roth
- 1997
|
|
51
|
On the complexity of domain-independent planning
– Erol, Nau, et al.
- 1992
|
|
48
|
Artificial economic life: a simple model of a stockmarket
– Palmer, Arthur, et al.
- 1994
|
|
45
|
Cognitive adaptations for social exchange
– Cosmides, Tooby
- 1992
|
|
42
|
High-Performance Job-Shop Scheduling With A Time-Delay TD(A) Network
– Zhang, Dietterich
- 1996
|
|
40
|
A Critical Review of Classifier Systems
– Wilson, Goldberg
- 1989
|
|
37
|
The role of heuristics in learning by discovery: Three case studies
– Lenat
- 1983
|
|
31
|
Multi-strategy learning of search control for partial-order planning
– Estlin, Mooney
- 1996
|
|
24
|
The Economy as an Evolving Complex System
– Anderson, Arrow, et al.
- 1988
|
|
24
|
Toward a model of mind as a laissez-faire economy of idiots
– Baum
- 1996
|
|
18
|
Learning to perceive and act
– Whitehead, Ballard
- 1991
|
|
15
|
On genetic algorithms, in
– Baum, Boneh, et al.
|
|
13
|
Hill climbing beats genetic search on a boolean circuit synthesis problem of koza's
– Lang
- 1995
|
|
11
|
Incremental Learning of Evaluation Functions for Absorbing Markov Chains: New Methods and Theorems
– Gurvits, Lin, et al.
- 1994
|
|
10
|
Representational Difficulties with Classifier Systems
– Schuurmans, Schaeffer
- 1989
|
|
10
|
Rationality
– VALIANT
- 1995
|
|
8
|
The working brain: an introduction to neuropsychology
– Luria
- 1973
|
|
8
|
Adaptation in dynamic environments through a minimal probability of exploration
– Venturini
- 1994
|
|
7
|
Implementing Semantic Networks Structures using the Classi�er System
– Forrest�
|
|
4
|
Steps towards Artificial Intelligence," Computers and Thought
– Minsky
- 1963
|
|
3
|
The SNLP planner implementation. Contact bugsnlp @cs.washington.edu
– Barrett, Weld
- 1990
|
|
2
|
Using temporal logic to control search in planning, unpublished document available from http://logos.uwaterloo.ca/tlplan/tlplan.html
– Bacchus, Kabanza
- 1995
|
|
2
|
Markets and Computation: Agoric Open Systems," The Ecology of Computation
– Miller, Drexler
- 1988
|
|
2
|
Roadkill on the information highway
– Myhrvold
- 1994
|
|
2
|
Practical issues in temporal difference learing
– Tesauro
- 1992
|
|
1
|
Esben Sloth, Evolutionary Economics: Post-Schumpeterian Contributions
– Andersen
- 1996
|
|
1
|
Economic Metalearning, submitted for publication
– Baum, Durdanovic
- 1997
|
|
1
|
issue of "Reason
– Coase
- 1997
|
|
