Self-improving reactive agents based on reinforcement learning, planning and teaching

1992/05/01 by Long-Ji Lin · 4 citations
Computer Science · Mathematics · #Adaptive Dynamic Programming Control #Artificial intelligence #Computer science #Evolutionary Algorithms and Applications #Generalization #Heuristic #Learning classifier system #Machine learning #Mathematics #Nondeterministic algorithm #Reinforcement Learning in Robotics #Reinforcement learning #Testbed #Theoretical computer science

paper · pdf · doi:10.1007/bf00992699

crossref issued 1992/05/01 · crossref published 1992/05/01 · crossref published-print 1992/05/01 · openalex publication_date 1992/05/01 · crossref created 2005/01/09 · crossref deposited 2024/01/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/31 · crossref indexed 2026/08/01

Citations

• A Learning Algorithm for Continually Running Fully Recurrent Neural Networks

Cited by

• Learning to Sequence Robot Behaviors for Visual Navigation
• Selective Pseudo-Labeling with Reinforcement Learning for Semi-Supervised Domain Adaptation
• Improved Regret Bound and Experience Replay in Regularized Policy Iteration
• Reinforcement learning [wikipedia]