Play to Grade: Testing Coding Games as Classifying Markov Decision Process.
Allen NieEmma BrunskillChris PiechPublished in: NeurIPS (2021)
Keyphrases
- markov decision process
- game playing
- state space
- temporal difference learning
- markov decision processes
- games played
- optimal policy
- reinforcement learning
- online game
- infinite horizon
- imperfect information
- finite horizon
- transition matrices
- video games
- game players
- initial state
- policy iteration
- reward function
- nash equilibria
- stochastic games
- human players
- average cost
- game theoretic
- nash equilibrium
- probabilistic model