Randomness conservation inequalities; information and independence in mathematical theories
Information and Control
Stochastic systems: estimation, identification and adaptive control
Stochastic systems: estimation, identification and adaptive control
Active perception and reinforcement learning
Neural Computation
Reinforcement learning in Markovian and non-Markovian environments
NIPS-3 Proceedings of the 1990 conference on Advances in neural information processing systems 3
Artificial Intelligence - Special issue on knowledge representation
Technical Note: \cal Q-Learning
Machine Learning
Learning in embedded systems
An introduction to Kolmogorov complexity and its applications
An introduction to Kolmogorov complexity and its applications
Reinforcement learning for robots using neural networks
Reinforcement learning for robots using neural networks
Deliberation scheduling for problem solving in time-constrained environments
Artificial Intelligence
Memoryless policies: theoretical limitations and practical results
SAB94 Proceedings of the third international conference on Simulation of adaptive behavior : from animals to animats 3: from animals to animats 3
Adding temporary memory to ZCS
Adaptive Behavior
Continual learning in reinforcement environments
Continual learning in reinforcement environments
PALO: a probabilistic hill-climbing algorithm
Artificial Intelligence
On the Length of Programs for Computing Finite Binary Sequences: statistical considerations
Journal of the ACM (JACM)
Learning to Predict by the Methods of Temporal Differences
Machine Learning
A Representation for the Adaptive Generation of Simple Sequential Programs
Proceedings of the 1st International Conference on Genetic Algorithms
Planning and Acting in Partially Observable Stochastic Domains
Planning and Acting in Partially Observable Stochastic Domains
Simple Principles of Metalearning
Simple Principles of Metalearning
The lack of a priori distinctions between learning algorithms
Neural Computation
Learning Team Strategies: Soccer Case Studies
Machine Learning
Reinforcement Learning Soccer Teams with Incomplete World Models
Autonomous Robots
EMCL '01 Proceedings of the 12th European Conference on Machine Learning
Learning to Learn Using Gradient Descent
ICANN '01 Proceedings of the International Conference on Artificial Neural Networks
Market-Based Reinforcement Learning in Partially Observable Worlds
ICANN '01 Proceedings of the International Conference on Artificial Neural Networks
Sequential Decision Making Based on Direct Search
Sequence Learning - Paradigms, Algorithms, and Applications
Advances in evolutionary computing
Optimal Ordered Problem Solver
Machine Learning
Probabilistic incremental program evolution
Evolutionary Computation
Why evolution is not a good paradigm for program induction: a critique of genetic programming
Proceedings of the first ACM/SIGEVO Summit on Genetic and Evolutionary Computation
Anticipatory Behavior in Adaptive Learning Systems
The neuronal replicator hypothesis
Neural Computation
A neural network model for inter-problem adaptive online time allocation
ICANN'05 Proceedings of the 15th international conference on Artificial neural networks: formal models and their applications - Volume Part II
A Monte-Carlo AIXI approximation
Journal of Artificial Intelligence Research
The automatic generation of mutation operators for genetic algorithms
Proceedings of the 14th annual conference companion on Genetic and evolutionary computation
2013 Special Issue: First experiments with PowerPlay
Neural Networks
Hi-index | 0.00 |
We study task sequences that allow for speeding up the learner‘saverage reward intake through appropriate shifts of inductive bias(changes of the learner‘s policy). To evaluate long-term effects ofbias shifts setting the stage for later bias shifts we use the“success-story algorithm” (SSA). SSA is occasionally called attimes that may depend on the policy itself. It uses backtracking toundo those bias shifts that have not been empirically observed totrigger long-term reward accelerations (measured up until the currentSSA call). Bias shifts that survive SSA represent a lifelong successhistory. Until the next SSA call, they are considered useful andbuild the basis for additional bias shifts. SSA allows for pluggingin a wide variety of learning algorithms. We plug in (1) a novel,adaptive extension of Levin search and (2) a method for embedding thelearner‘s policy modification strategy within the policy itself(incremental self-improvement). Our inductive transfer case studiesinvolve complex, partially observable environments where traditionalreinforcement learning fails.