BCPO combines a variational information bottleneck encoder with SAC for context-based RL, but the supporting theory's ELBO derivation is flawed and the performance claims are overstated.
Sim-to-real transfer of robotic control with dynamics randomization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Observations Meet Actions: Learning Control-Sufficient Representations for Robust Policy Generalization
BCPO combines a variational information bottleneck encoder with SAC for context-based RL, but the supporting theory's ELBO derivation is flawed and the performance claims are overstated.