Co-evolving parasites improve simulated evolution as an optimization procedure
CNLS '89 Proceedings of the ninth annual international conference of the Center for Nonlinear Studies on Self-organizing, Collective, and Cooperative Phenomena in Natural and Artificial Computing Networks on Emergent computation
A possibility for implementing curiosity and boredom in model-building neural controllers
Proceedings of the first international conference on simulation of adaptive behavior on From animals to animats
Neural networks and the bias/variance dilemma
Neural Computation
Information-based objective functions for active data selection
Neural Computation
Learning factorial codes by predictability minimization
Neural Computation
Reinforcement learning for robots using neural networks
Reinforcement learning for robots using neural networks
TD-Gammon, a self-teaching backgammon program, achieves master-level play
Neural Computation
Hierarchical chunking in classifier systems
AAAI'94 Proceedings of the twelfth national conference on Artificial intelligence (vol. 2)
Neural Computation
An introduction to Kolmogorov complexity and its applications (2nd ed.)
An introduction to Kolmogorov complexity and its applications (2nd ed.)
Machine Learning - Special issue on inductive transfer
Reinforcement learning with self-modifying policies
Learning to learn
Toward a Model of Intelligence as an Economy of Agents
Machine Learning
On the Length of Programs for Computing Finite Binary Sequences: statistical considerations
Journal of the ACM (JACM)
Using collective intelligence to route Internet traffic
Proceedings of the 1998 conference on Advances in neural information processing systems II
A mathematical theory of communication
ACM SIGMOBILE Mobile Computing and Communications Review
Proceedings of the Workshop on Adaption and Learning in Multi-Agent Systems
IJCAI '95 Proceedings of the Workshop on Adaption and Learning in Multi-Agent Systems
Properties of the Bucket Brigade
Proceedings of the 1st International Conference on Genetic Algorithms
Unsupervised Discrimination of Clustered Data via Optimization of Binary Information Gain
Advances in Neural Information Processing Systems 5, [NIPS Conference]
Facial beauty and fractal geometry
Facial beauty and fractal geometry
What''s interesting?
Classifier fitness based on accuracy
Evolutionary Computation
Semilinear predictability minimization produces well-known feature detectors
Neural Computation
Optimal Ordered Problem Solver
Machine Learning
Coordinating with the Future: The Anticipatory Nature of Representation
Minds and Machines
ALT '07 Proceedings of the 18th international conference on Algorithmic Learning Theory
Anticipatory Behavior in Adaptive Learning Systems
DS'07 Proceedings of the 10th international conference on Discovery science
Evolving plastic neural networks with novelty search
Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Abandoning objectives: Evolution through the search for novelty alone
Evolutionary Computation
Emergence of safe behaviours with an intrinsic reward
ICAIS'11 Proceedings of the Second international conference on Adaptive and intelligent systems
Procedural content generation for games: A survey
ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)
2013 Special Issue: First experiments with PowerPlay
Neural Networks
Curiosity: From psychology to computation
ACM Computing Surveys (CSUR)
Hi-index | 0.00 |
Details of complex event sequences are often not predictable, but their reduced abstract representations are. I study an embedded active learner that can limit its predictions to almost arbitrary computable aspects of spatio-temporal events. It constructs probabilistic algorithms that (1) control interaction with the world, (2) map event sequences to abstract internal representations (IRs), (3) predict IRs from IRs computed earlier. Its goal is to create novel algorithms generating IRs useful for correct IR predictions, without wasting time on those learned before. This requires an adaptive novelty measure which is implemented by a co-evolutionary scheme involving two competing modules collectively designing (initially random) algorithms representing experiments. Using special instructions, the modules can bet on the outcome of IR predictions computed by algorithms they have agreed upon. If their opinions differ then the system checks who's right, punishes the loser (the surprised one), and rewards the winner. An evolutionary or reinforcement learning algorithm forces each module to maximize reward. This motivates both modules to lure each other into agreeing upon experiments involving predictions that surprise it. Since each module essentially can veto experiments it does not consider profitable, the system is motivated to focus on those computable aspects of the environment where both modules still have confident but different opinions. Once both share the same opinion on a particular issue (via the loser's learning process, e.g., the winner is simply copied onto the loser), the winner loses a source of reward -- an incentive to shift the focus of interest onto novel experiments. My simulations include an example where surprise-generation of this kind helps to speed up external reward.