Using VizDoom Research Platform Scenarios for Benchmarking Reinforcement Learning Algorithms in First-Person Shooter Games.
Adil KhanAsghar Ali ShahLal KhanMuhammad Rehan FaheemMuhammad NaeemHsien-Tsung ChangPublished in: IEEE Access (2024)
Keyphrases
- reinforcement learning algorithms
- video games
- computer games
- stochastic games
- reinforcement learning
- markov decision processes
- model free
- state space
- reinforcement learning problems
- reinforcement learning methods
- function approximation
- temporal difference
- learning algorithm
- learning experience
- multiagent reinforcement learning
- eligibility traces
- policy search
- game playing
- neural network
- partially observable environments
- learning agent
- reward function
- dynamic environments
- monte carlo
- imperfect information
- markov chain
- dynamic programming