RC-aux corrects spatiotemporal mismatch in reconstruction-free latent world models by adding multi-horizon prediction and reachability supervision, improving planning performance on goal-conditioned pixel-control tasks.
Mudreamer: Learning predictive world models without recon- struction.arXiv preprint arXiv:2405.15083
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.LG 3years
2026 3verdicts
UNVERDICTED 3roles
baseline 1polarities
baseline 1representative citing papers
Dreamer-CDP achieves reconstruction-free world modeling via a JEPA-style predictor on continuous deterministic representations and matches Dreamer's performance on Crafter.
The work introduces behavior-invariant latent task representations via information-theoretic learning in a Transformer world model plus conservative penalties on imagined rollouts to improve generalization in offline meta-RL.
citing papers explorer
-
Predictive but Not Plannable: RC-aux for Latent World Models
RC-aux corrects spatiotemporal mismatch in reconstruction-free latent world models by adding multi-horizon prediction and reachability supervision, improving planning performance on goal-conditioned pixel-control tasks.
-
Dreamer-CDP: Improving Reconstruction-free World Models Via Continuous Deterministic Representation Prediction
Dreamer-CDP achieves reconstruction-free world modeling via a JEPA-style predictor on continuous deterministic representations and matches Dreamer's performance on Crafter.
-
Behavior-Invariant Task Representation Learning with Transformer-based World Models for Offline Meta-Reinforcement Learning
The work introduces behavior-invariant latent task representations via information-theoretic learning in a Transformer world model plus conservative penalties on imagined rollouts to improve generalization in offline meta-RL.