A latent world model combined with off-policy SAC, short latent rollouts, and n-step targets outperforms DreamerV3, SAC, and PPO in MetaDrive driving, with the best results at a five-step rollout horizon.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Dreamer-SAC: Off-Policy Learning in Latent World Models for Sample-Efficient Autonomous Driving
A latent world model combined with off-policy SAC, short latent rollouts, and n-step targets outperforms DreamerV3, SAC, and PPO in MetaDrive driving, with the best results at a five-step rollout horizon.