RAID finds multiple diverse game exploits by sequentially training RL agents and masking previously discovered strategies from the reward function.
Discovering policies with DOMiNO: Diversity optimization maintaining near optimality,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Reward-Adaptive Iterative Discovery: A Case Study on Automated Game Testing for NHL26
RAID finds multiple diverse game exploits by sequentially training RL agents and masking previously discovered strategies from the reward function.