A time-conditioned world model trained on mixed time steps matches or beats a fixed-time-step baseline at its native rate and far exceeds it at slower observation rates, using the same sample count.
Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Time-Aware World Model for Adaptive Prediction and Control
A time-conditioned world model trained on mixed time steps matches or beats a fixed-time-step baseline at its native rate and far exceeds it at slower observation rates, using the same sample count.