Graph-based RL agents can solve logic puzzles larger than anything seen in training, with graph structure, reward design, and recurrence each changing how far extrapolation goes.
S.; Courville, A.; and Bellemare, M
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
-
Beyond Interpolation: Extrapolative Reasoning with Reinforcement Learning and Graph Neural Networks
Graph-based RL agents can solve logic puzzles larger than anything seen in training, with graph structure, reward design, and recurrence each changing how far extrapolation goes.