Bayesian Inverse Reinforcement Learning for Non-Markovian Rewards.
Noah TopperAlvaro VelasquezGeorge K. AtiaPublished in: CoRR (2024)
Keyphrases
- reward function
- inverse reinforcement learning
- bayesian nonparametric
- markov decision processes
- reinforcement learning
- partially observable environments
- state space
- reinforcement learning algorithms
- multiple agents
- partially observable
- optimal policy
- transition probabilities
- state variables
- markov decision process
- simple examples
- bayesian networks
- posterior probability
- bayesian inference
- generative model
- dynamic programming
- markov chain
- np hard