Zero-shot sharing of obstacle-recovery macros picked by a causal effect model lets grid-world agents bridge about half of the gap between random exploration and full retraining, but only in some goal and barrier configurations.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Causal Knowledge Transfer for Multi-Agent Reinforcement Learning in Dynamic Environments
Zero-shot sharing of obstacle-recovery macros picked by a causal effect model lets grid-world agents bridge about half of the gap between random exploration and full retraining, but only in some goal and barrier configurations.