Reinforcement Learning for Scriptless Testing: An Empirical Investigation of Reward Functions.
Olivia Rodriguez ValdésTanja E. J. VosBeatriz MarínPekka AhoPublished in: RCIS (2023)
Keyphrases
- reward function
- reinforcement learning
- reinforcement learning algorithms
- policy search
- state space
- markov decision processes
- optimal policy
- markov decision process
- partially observable
- inverse reinforcement learning
- transition probabilities
- learning agents
- state variables
- multiple agents
- markov decision problems
- machine learning
- function approximation
- state action
- learning algorithm
- markov chain
- continuous state
- multi agent
- dynamic programming
- policy iteration
- search algorithm
- simple examples