Multi-Objective Deep Inverse Reinforcement Learning through Direct Weights and Rewards Estimation.
Daiko KishikawaSachiyo AraiPublished in: SICE (2022)
Keyphrases
- multi objective
- inverse reinforcement learning
- reward function
- evolutionary algorithm
- bayesian nonparametric
- partially observable environments
- reinforcement learning
- objective function
- markov decision processes
- particle swarm optimization
- gaussian process
- preference elicitation
- multi criteria
- temporal difference
- multiple objectives
- state space
- reinforcement learning algorithms
- neural network
- genetic algorithm