Automatic Evaluation of Excavator Operators using Learned Reward Functions.
Pranav AgarwalMarek TeichmannSheldon AndrewsSamira Ebrahimi KahouPublished in: CoRR (2022)
Keyphrases
- automatic evaluation
- reward function
- markov decision processes
- inverse reinforcement learning
- human judgments
- quality assessment
- state variables
- transition probabilities
- multiple agents
- reinforcement learning
- state space
- machine learning
- information retrieval
- optimal policy
- human subjects
- prior knowledge
- search space