Statistical Reinforcement Learning: Modern Machine Learning Approaches
Reinforcement learning is a mathematical framework for developing computer agents that can learn an optimal behavior by relating generic reward signals with its past actions. With numerous successful applications in business intelligence, plant control, and gaming, the RL framework is ideal for decision making in unknown environments with large amo
What people are saying - Write a review
We haven't found any reviews in the usual places.
Other editions - View all
action agent algorithm angle approach approximation average baseline basis functions bound brush called centers Chapter chosen collected computed conditional consider consists continuous defined denotes density dimensionality reduction direct policy search distribution environment episodes error estimator evaluation example explained Figure flattening parameter Gaussian Gaussian kernels GGKs given goal gradient gradient estimators graph hand immediate reward importance weight improvement increasing initial introduced IW-PGPE IWCV joint least-squares length loss LSCDE machine learning matrix maximizer mean method move natural noise Note obtained optimal ordinary parameter performance PGPE pitch policy iteration policy parameter policy-prior positive practice probability problem reaching reinforcement learning respect reuse robot runs samples sampling policy shape shown shows solution space state-action step strokes takes task tends trajectory trajectory samples transition trials true update value function variance vector