World Model Control by Trajectory Reachability Metrics
cs.LG, cs.RO
Submitted: 2026-05-21
Updated: 2026-08-31
Comments: 24 pages, including appendix
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- TLDR: Unsupervised Goal-Conditioned RL via Temporal Distance-Aware Representations
- Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models
- Search on the Replay Buffer: Bridging Planning and Reinforcement Learning
- Dream to Control: Learning Behaviors by Latent Imagination
- Predictive but Not Plannable: RC-aux for Latent World Models
- LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
- stable-worldmodel-v1: Reproducible World Modeling Research and Evaluation
- Offline Goal-conditioned Reinforcement Learning with Quasimetric Representations
- Goal-Conditioned Reinforcement Learning with Disentanglement-based Reachability Planning
- LEPA: Learning Geometric Equivariance in Satellite Remote Sensing Data with a Predictive Architecture
- DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks