Parallelization of Reinforcement Learning Algorithms for Video Games.
Marek KopelWitold SzczurekPublished in: ACIIDS (2021)
Keyphrases
- video games
- reinforcement learning algorithms
- reinforcement learning
- state space
- markov decision processes
- model free
- reinforcement learning problems
- game play
- eligibility traces
- learning experience
- temporal difference
- learning algorithm
- function approximation
- reinforcement learning methods
- educational games
- reward function
- game design
- serious games
- computer games
- partially observable environments
- game playing
- dynamic environments
- commercial games
- neural network
- reward shaping
- policy search
- decision making
- mathematics learning
- multi agent
- evaluation function