LTL-Based Non-Markovian Inverse Reinforcement Learning.
Mohammad AfzalSankalp GambhirAshutosh GuptaKrishna SAshutosh TrivediAlvaro VelasquezPublished in: AAMAS (2023)
Keyphrases
- inverse reinforcement learning
- reward function
- bayesian nonparametric
- model checking
- temporal logic
- reinforcement learning
- markov decision processes
- partially observable environments
- state space
- reinforcement learning algorithms
- multiple agents
- optimal policy
- partially observable
- preference elicitation
- simple examples
- transition probabilities
- situation calculus
- markov decision process
- temporal difference
- temporally extended
- classical planning
- generative model
- control policies
- finite state
- special case
- machine learning