DAGS initializes policy-gradient self-play from human-derived intermediate states to reduce exploitability in challenging imperfect-information games, with a multi-task flag fix for resulting bias and new benchmark environments.
Proceedings of the 40th International Conference on Machine Learning , pages =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Data-Augmented Game Starts for Accelerating Self-Play Exploration in Imperfect Information Games
DAGS initializes policy-gradient self-play from human-derived intermediate states to reduce exploitability in challenging imperfect-information games, with a multi-task flag fix for resulting bias and new benchmark environments.