The authors built AD-WM, a joint-embedding world model with residual latent dynamics and two auxiliary action-recovery objectives: inverse dynamics and normalized recovery motivated by conditional mutual information.
Action-discriminative world models improve counterfactual planning for robot control
Training latent dynamics to preserve action-specific differences substantially improved model predictive control in simulation and zero-shot robot transfer.
Top University
Nanjing University
Research Digest··2 min read
Qiu et al.
Why this paper
From Nanjing University
In one line
World models for planning should preserve action-dependent differences for counterfactual selection, not just factual prediction accuracy.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ✓Reports numbers on named benchmarks (2 benchmarks)
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§