(More) efficient reinforcement learning via posterior sampling

INIS

• learning 100%
• algorithms 85%
• sampling 71%
• exploration 28%
• space 14%
• simulation 14%
• policy 14%
• length 14%
• distribution 14%
• markov process 14%

Computer Science

• Reinforcement Learning 100%
• Algorithms 57%
• And-States 28%
• Learning Algorithm 28%
• Prior Knowledge 14%
• Prior Distribution 14%
• Simulation 14%
• Cardinality 14%

Neuroscience

• Reinforcement Learning 100%