Toward Computationally Efficient Inverse Reinforcement Learning via Reward Shaping.
Lauren H. CookeHarvey KlyneEdwin ZhangCassidy LaidlawMilind TambeFinale Doshi-VelezPublished in: CoRR (2023)
Keyphrases
- inverse reinforcement learning
- reward shaping
- reward function
- reinforcement learning
- reinforcement learning algorithms
- markov decision processes
- state space
- multiple agents
- optimal policy
- temporal difference
- partially observable
- complex domains
- preference elicitation
- transition probabilities
- markov decision problems
- learning agent
- transition model
- state variables
- generative model
- markov decision process
- average cost
- monte carlo
- random walk
- function approximation