Solving the scalarization issues of Advantage-based Reinforcement Learning algorithms.
Federico A. GalatoloMario G. C. A. CiminoGigliola VagliniPublished in: Comput. Electr. Eng. (2021)
Keyphrases
- reinforcement learning algorithms
- reinforcement learning
- model free
- markov decision processes
- state space
- learning algorithm
- reinforcement learning problems
- dynamic environments
- temporal difference
- eligibility traces
- policy search
- markov decision problems
- partially observable environments
- reinforcement learning methods
- multi objective
- function approximators
- reward function
- solving problems
- evolutionary algorithm
- machine learning
- data mining