Meta-algorithm for co-training policies from two views in RL and IL, with sufficient conditions for improvement over single-view learning.
The max-cut prob- lem and quadratic 0–1 optimization; polyhedral aspects, relaxations and bounds
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Co-training for Policy Learning
Meta-algorithm for co-training policies from two views in RL and IL, with sufficient conditions for improvement over single-view learning.