Toward a Model of Mind as a Laissez-Faire Economy of Idiots
@inproceedings{Baum1996TowardAM, title={Toward a Model of Mind as a Laissez-Faire Economy of Idiots}, author={Eric B. Baum}, booktitle={ICML}, year={1996} }
A learning machine called \The Hayek Machine" is proposed and tested on a simulated Blocks World planning problem. [] Key Method First, the market price learns to estimate Hayek's future reward from using a given agent. Second, the market automatically selects the agent with highest estimate to act next. Third, new agents can enter the market if and only if they have greater expected utility than direct competitors. Hayek learns by gradual accretion of useful agents and elimination of poor ones,and by…
No Paper Link Available
37 Citations
Toward a Model of Intelligence as an Economy ofIdiots
- Computer Science
- 1997
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…
Toward a Model of Intelligence as an Economy of Agents
- Computer ScienceMachine Learning
- 2004
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…
A Survey of Collective Intelligence
- Computer Science
- 2013
COIN science is presented, which has already resulted in successes in artificial domains, in particular in packet-routing, the leader-follower problem, and in variants of Arthur's "El Farol bar problem".
An Introduction to Collective Intelligence
- Computer ScienceArXiv
- 1999
This paper surveys the emerging science of how to design a “COllective INtelligence” (COIN). A COIN is a large multi-agent system where: i) There is little to no centralized communication or control.…
Evolution of Cooperative Problem Solving in an Artificial Economy
- Computer ScienceNeural Computation
- 2000
It is found empirically that starting from programs that are random computer code, the economy can develop systems that solve hard problems and learns to solve almost all random Blocks World problems with goal stacks that are 200 blocks high.
Learning to Play Using Low-Complexity Rule-Based Policies: Illustrations through Ms. Pac-Man
- Computer ScienceJ. Artif. Intell. Res.
- 2007
This article defines a set of high-level observation and action modules, from which rule-based policies are constructed automatically, and argues that learning is successful mainly because policies may apply concurrent actions and thus the policy space is sufficiently rich.
Decentralized Reinforcement Learning: Global Decision-Making via Local Economic Transactions
- Computer ScienceICML
- 2020
A class of decentralized reinforcement learning algorithms are derived that are broadly applicable not only to standard reinforcement learning but also for selecting options in semi-MDPs and dynamically composing computation graphs.
The Society of Mind Requires an Economy of Mind
- Economics
- 1997
A society of mind will require an economy of mind, that is multi-agent systems (MAS) that meet a requirement for the adaptive allocation and reallocation of scarce resources will need to use a…
The World-Wide-Mind: Draft Proposal
- Computer Science
- 2001
This paper shows how previous models of mind where competition took place between extremely incompatible components, and where the mind could survive communications failure with or even complete loss of a number of such components are the type of models needed in the WWM.
References
SHOWING 1-10 OF 61 REFERENCES
The Role of Heuristics in Learning by Discovery: Three Case Studies
- Business
- 1983
As artificial intelligence (AI) programs are called upon to exhibit increasingly complex behaviors, their builders are faced with the growing task of inserting more and more knowledge into the…
Learning to reason
- Computer ScienceJACM
- 1997
This work introduces a new framework for the study of reasoning, and gives Learning to Reason algorithms for classes of propositional languages for which there are no efficient reasoning algorithms, when represented as a traditional (formula-based) knowledge base.
Learning to Perceive and Act
- Computer Science
- 1990
This paper considers adaptive control architectures that integrate active sensory-motor systems with decision systems based on reinforcement learning and shows that the phenomenon perceptual aliasing destabilizes existing reinforcement learning algorithms with respect to the optimal decision policy.
The Economy as an Evolving Complex System II
- Economics
- 1988
* Introduction W.B. Arthur, S.N., Durlauf, and D. Lane * Asset Pricing Under Endogenous Expectations in an Artificial Stock Market W.B. Arthur, J.H. Holland, B. LeBaron, R. Palmer, and P. Tayler *…
Learning to Act Using Real-Time Dynamic Programming
- Computer ScienceArtif. Intell.
- 1995
Autonomous theory building systems
- Computer ScienceAnn. Oper. Res.
- 1995
This work describes autonomous systems, which observe the outside world and try to generate programs which reproduce the observed data, as well as methods for generation of new programs, which are enumeration, mutation and combination of old programs.
Cognitive adaptations for social exchange.
- Psychology, Biology
- 1992
It is argued that humans have a faculty of social cognition, consisting of a rich collection of dedicated, functionally specialized, interrelated modules organized to collectively guide thought and behavior with respect to the evolutionarily recurrent adaptive problems posed by the social world.
The ecology of computation
- MathematicsDigest of Papers. COMPCON Spring 89. Thirty-Fourth IEEE Computer Society International Conference: Intellectual Leverage
- 1989
The author has developed a perspective on computational ecologies as well as a theory of their behavior which explicitly takes into account incomplete knowledge and delayed information on the part of its agents.
Understanding natural language
- Computer Science
- 1972
A computer system for understanding English that contains a parser, a recognition grammar of English, programs for semantic analysis, and a general problem solving system based on the belief that in modeling language understanding, it must deal in an integrated way with all of the aspects of language—syntax, semantics, and inference.