Publication | Closed Access
HQ-Learning
164
Citations
27
References
1997
Year
Artificial IntelligenceEngineeringMachine LearningReactive SubagentsEducationReinforcement Learning (Educational Psychology)Intelligent SystemsMulti-agent LearningLifelong Reinforcement LearningReinforcement Learning (Computer Engineering)Data ScienceHierarchical ExtensionRobot LearningHuman LearningMemoryless PoliciesSequential Decision MakingComputer ScienceMarkov Decision ProcessDeep Reinforcement Learning
HQ-learning is a hierarchical extension of Q(λ)-learning designed to solve certain types of partially observable Markov decision problems (POMDPs). HQ automatically decomposes POMDPs into sequences of simpler subtasks that can be solved by memoryless policies learnable by reactive subagents. HQ can solve partially observable mazes with more states than those used in most previous POMDP work.
| Year | Citations | |
|---|---|---|
Page 1
Page 1