Reinforcement Learning: Improve Feedback Mechanism with Indicator based Reward, VirtualTA towards Growth Mindset.
Zhiyi LiPublished in: SIGCSE (2019)
Keyphrases
- reinforcement learning
- state space
- function approximation
- machine learning
- selection mechanism
- reinforcement learning algorithms
- optimal policy
- learning mechanism
- reward function
- eligibility traces
- data sets
- policy gradient
- temporal difference
- model free
- markov decision processes
- dynamic programming
- hidden markov models
- learning process
- multi agent systems