(4)Reinforcement Learning-1 Reinforcement learning Inspired by behaviorist psychology,concerned with how software agents ought to take actions in an environment so as to maximize some notion of cumulative reward. Approximate dynamic programming ●game theory,control theory,operations research,information theory,simulation-based optimization,multi-agent systems, swarm intelligence,statistics,and genetic algorithms. 12 Copyright 2019 by Xiaoyu Li
Copyright © 2019 by Xiaoyu Li. 12 （4）Reinforcement Learning-1 Reinforcement learning Inspired by behaviorist psychology, concerned with how software agents ought to take actions in an environment so as to maximize some notion of cumulative reward. Approximate dynamic programming game theory, control theory, operations research,information theory, simulation-based optimization, multi-agent systems, swarm intelligence, statistics, and genetic algorithms
(4)Reinforcement Learning-2 The basic reinforcement learning model consists of; a set of environment states S; a set of actions 4; rules of transitioning between states; rules that determine the scalar immediate reward of a transition; rules that describe what the agent observes. ATA 13 Copyright 2019 by Xiaoyu Li
Copyright © 2019 by Xiaoyu Li. 13 The basic reinforcement learning model consists of: a set of environment states S; a set of actions A; rules of transitioning between states; rules that determine the scalar immediate reward of a transition; rules that describe what the agent observes. （4）Reinforcement Learning-2
(4)Reinforcement Learning-3 Reinforcement learning good! 4 14 DATA Copyright 2019 by Xiaoyu Li
Copyright © 2019 by Xiaoyu Li. 14 Reinforcement learning （4）Reinforcement Learning-3
3.2 Least Square Method 15 DATA Copyright 2019 by Xiaoyu Li
Copyright © 2019 by Xiaoyu Li. 15 3.2 Least Square Method
Data fitting example 15 10 20-10 10 20 30 40 50 60 Random data points and their linear fitting ATA 16 Copyright 2019 by Xiaoyu Li
Copyright © 2019 by Xiaoyu Li. 16 Data fitting example Random data points and their linear fitting