State Space Closure: Revisiting Endless Online Level Generation via Reinforcement Learning.
Ziqi WangTianye ShuJialin LiuPublished in: CoRR (2022)
Keyphrases
- state space
- reinforcement learning
- reinforcement learning algorithms
- markov decision processes
- online learning
- optimal policy
- heuristic search
- dynamic programming
- function approximation
- machine learning
- markov decision problems
- markov decision process
- state variables
- multi agent
- real time
- markov chain
- model free
- search space
- control problems
- dynamical systems
- higher level
- generation process
- partially observable
- initial state
- continuous state spaces
- state abstraction
- balancing exploration and exploitation