On the Limitations of Markovian Rewards to Express Multi-Objective, Risk-Sensitive, and Modal Tasks.
Joar SkalseAlessandro AbatePublished in: CoRR (2024)
Keyphrases
- multi objective
- risk sensitive
- markov decision processes
- evolutionary algorithm
- multi objective optimization
- optimal control
- reinforcement learning
- objective function
- optimization algorithm
- optimality criterion
- multiple objectives
- utility function
- model free
- dynamic programming
- state space
- neural network
- modal logic
- optimal solution
- decision theoretic
- control policies
- efficient optimization