Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations
Subgrouping reduces complexity and speeds up learning in recurrent networks
Advances in neural information processing systems 2
Language as a dynamical system
Mind as motion
Neural Networks: A Comprehensive Foundation
Neural Networks: A Comprehensive Foundation
Learning and discovery of predictive state representations in dynamical systems with reset
ICML '04 Proceedings of the twenty-first international conference on Machine learning
Learning low dimensional predictive representations
ICML '04 Proceedings of the twenty-first international conference on Machine learning
TD(λ) networks: temporal-difference networks with eligibility traces
ICML '05 Proceedings of the 22nd international conference on Machine learning
Learning predictive state representations in dynamical systems without reset
ICML '05 Proceedings of the 22nd international conference on Machine learning
Observable Operator Models for Discrete Stochastic Time Series
Neural Computation
A learning algorithm for continually running fully recurrent neural networks
Neural Computation
On-line discovery of temporal-difference networks
Proceedings of the 25th international conference on Machine learning
Planning in models that combine memory with predictive representations of state
AAAI'05 Proceedings of the 20th national conference on Artificial intelligence - Volume 2
Temporal-difference networks with history
IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
A Monte-Carlo AIXI approximation
Journal of Artificial Intelligence Research
| Hi-index | 0.00 |
We propose a new neural network architecture, called Simple Recurrent Temporal-Difference Networks (SR-TDNs), that learns to predict future observations in partially observable environments. SR-TDNs incorporate the structure of simple recurrent neural networks (SRNs) into temporal-difference (TD) networks to use proto-predictive representation of states. Although they deviate from the principle of predictive representations to ground state representations on observations, they follow the same learning strategy as TD networks, i.e., applying TD-learning to general predictions. Simulation experiments revealed that SR-TDNs can correctly represent states with an incomplete set of core tests (question networks), and consequently, SR-TDNs have better on-line learning capacity than TD networks in various environments.