Dynamics-Informed Action Learning for Goal-Conditioned Latent Planning
Overview
This research paper presents Dynamics-Informed Action Learning (DIAL), a novel approach designed to address the disconnect between learning latent dynamics and utilizing them for planning in visual control tasks. The authors propose training methods that expose forward models to autoregressive predictions and train an inverse dynamics head to infer actions from latent-state transitions. At test time, DIAL couples these dynamics to initialize action sequences for the Cross-Entropy Method (CEM), refining the search towards a goal. Experiments on four visual control benchmarks show that DIAL outperforms existing latent world models and planning baselines in both standard and long-horizon scenarios.
Generated from attributed reports · Updated 5 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
No current evidence-backed claims. Missing information remains not reported.
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalDynamics-Informed Action Learning for Goal-Conditioned Latent Planning
This research paper presents Dynamics-Informed Action Learning (DIAL), a novel approach designed to address the disconnect between learning latent dynamics and utilizing them for planning in visual control tasks. The authors propose training methods that expose forward models to autoregressive predictions and train an inverse dynamics head to infer actions from latent-state transitions. At test time, DIAL couples these dynamics to initialize action sequences for the Cross-Entropy Method (CEM), refining the search towards a goal. Experiments on four visual control benchmarks show that DIAL outperforms existing latent world models and planning baselines in both standard and long-horizon scenarios.
Event coverage history
There is not enough continuous observation data to show a trend.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).