A DRL-based automated testing framework is shown to distinguish between GA-based and random procedural content generation in a serious game, with GA versions yielding higher agent win rates.
The agents are then trained against three SG versions and checkpoints are saved throughout training
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A modular framework for automated evaluation of procedural content generation in serious games with deep reinforcement learning agents
A DRL-based automated testing framework is shown to distinguish between GA-based and random procedural content generation in a serious game, with GA versions yielding higher agent win rates.