scientific article; zbMATH DE number 836011

MaRDI QIDQ4861477zbMATH OpenFDO

Authors Mark B. Ring

Publication date 22 January 1996

zbMATH Keywords

continual learninglearning algorithmtemporal transition hierarchies

Mathematics Subject Classification ID

Research exposition (monographs, survey articles) pertaining to computer science (68-02) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• CHILD: A first step towards continual learning
• Reinforcement learning agents
• Algorithms for reinforcement learning.
• scientific article; zbMATH DE number 527264
• TEXPLORE: temporal difference reinforcement learning for robots and time-constrained domains

Cited in

(10)

• CHILD: A first step towards continual learning
• Map learning with uninterpreted sensors and effectors
• Sequential changepoint detection in neural networks with checkpoints
• Continual curiosity-driven skill acquisition from high-dimensional video inputs for humanoid robots
• Addressing environment non-stationarity by repeating Q-learning updates
• Self-Sustaining Iterated Learning
• Evaluating robustness in a two layer simulated robot architecture
• The inverse variance-flatness relation in stochastic gradient descent is critical for finding flat minima
• Optimal Curiosity-Driven Modular Incremental Slow Feature Analysis
• Adaptive few-shot class-incremental learning via latent variable models

This page was built for publication:

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4861477)