Multilayer feedforward networks are universal approximators
Neural Networks
The cascade-correlation learning architecture
Advances in neural information processing systems 2
Universal approximation using radial-basis-function networks
Neural Computation
Technical Note: \cal Q-Learning
Machine Learning
Reinforcement learning with replacing eligibility traces
Machine Learning - Special issue on reinforcement learning
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Evolving neural networks through augmenting topologies
Evolutionary Computation
Spike-Timing-Dependent Hebbian Plasticity as Temporal Difference Learning
Neural Computation
Compositional pattern producing networks: A novel abstraction of development
Genetic Programming and Evolvable Machines
Mathematical properties of neuronal TD-rules and differential Hebbian learning: a comparison
Biological Cybernetics
Accelerated Neural Evolution through Cooperatively Coevolved Synapses
The Journal of Machine Learning Research
A unifying framework for computational reinforcement learning theory
A unifying framework for computational reinforcement learning theory
Indirectly encoding neural plasticity as a pattern of local rules
SAB'10 Proceedings of the 11th international conference on Simulation of adaptive behavior: from animals to animats
Evolving plastic neural networks with novelty search
Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Learnability, Stability and Uniform Convergence
The Journal of Machine Learning Research
Abandoning objectives: Evolution through the search for novelty alone
Evolutionary Computation
Encouraging behavioral diversity in evolutionary robotics: An empirical study
Evolutionary Computation
Survey: Reservoir computing approaches to recurrent neural network training
Computer Science Review
| Hi-index | 0.00 |
We consider the problem of designing local reinforcement learning rules for artificial neural network ANN controllers. Motivated by the universal approximation properties of ANNs, we adopt an ANN representation for the learning rules, which are optimized using evolutionary algorithms. We evaluate the ANN rules in partially observable versions of four tasks: the mountain car, the acrobot, the cart pole balancing, and the nonstationary mountain car. For testing whether such evolved ANN-based learning rules perform satisfactorily, we compare their performance with the performance of SARSA with tile coding, when the latter is provided with either full or partial state information. The comparison shows that the evolved rules perform much better than SARSA with partial state information and are comparable to the one with full state information, while in the case of the nonstationary environment, the evolved rule is much more adaptive. It is therefore clear that the proposed approach can be particularly effective in both partially observable and nonstationary environments. Moreover, it could potentially be utilized toward creating more general rules that can be applied in multiple domains and transfer learning scenarios.