The paper introduces a hierarchical model-based reinforcement learning framework that learns control policies from action-free time series by exploiting shared dynamics across related systems. It uses low-dimensional dynamical embeddings to capture both shared structure and individual variation, which then parameterize shared policy and value networks. Experiments on Lorenz-63, double-pendulum, and neural-behavioral data show that these hierarchical policies outperform independently trained ones, achieve higher rewards than planning with the same models, and generalize to unseen systems using only embedding inference.
arXiv:2602. 12643v2 Announce Type: replace-cross Abstract: We present Unified Latent Dynamics (ULD), a novel reinforcement learning algorithm that unifies the efficiency of model-free methods with the representational strengths of model-based approaches, without incurring planning overhead.
arXiv:2606. 03017v1 Announce Type: cross Abstract: Reward transfer in Inverse Reinforcement Learning (IRL) is unreliable when policies must generalize to unseen combinations of environment dynamics and task goals.
arXiv:2609.38598v1 Announce Type: new Abstract: Partially observable environments pose a fundamental challenge in deep reinforcement learning, requiring agents to compress temporal information from o...
arXiv:2606. 20104v1 Announce Type: cross Abstract: Perception for action suggests that representations of the world should be shaped not by visual fidelity alone, but by their relevance for actions.
arXiv:2608. 05989v1 Announce Type: new Abstract: Sample-efficient policy learning from pixels is a long-standing challenge in reinforcement learning (RL).
Sample-efficient policy learning from pixels is a long-standing challenge in reinforcement learning (RL). Recent dynamics-based representation learning methods have significantly improved the sample efficiency of model-free visual RL by learning dynamics-aware representations through auxiliary prediction performed either in latent space (self-prediction) or observation space (observation prediction).
arXiv:2609.21108v1 Announce Type: new Abstract: Deep reinforcement learning (DRL) has achieved strong performance across a wide range of continuous-control problems. These continuous-control policies...
arXiv:2607. 27138v1 Announce Type: cross Abstract: Vision-language-action (VLA) models remain constrained by scarce action-labeled robot data, whereas action-free videos offer abundant observations of physical change.
arXiv:2606. 12200v1 Announce Type: cross Abstract: We study policy representation learning from unlabeled multi-policy behavioral data.
arXiv:2607. 22430v1 Announce Type: new Abstract: Learning world models that infer environment dynamics from high-dimensional observations and predict outcomes under candidate actions is central to planning and control.
The paper investigates how small action errors evolve when using action chunking in behavioural cloning. By injecting errors at each state and observing their growth under open‑loop (no replanning) and closed‑loop (replanning) regimes, the authors classify states as contracting, expanding, or unresolved. Across twelve manipulation tasks, they find that stable states are rare, error amplification is common, and that short‑horizon fitting can overestimate long‑horizon propagation. Predictors trained on camera and proprioceptive data can recover open‑loop stability but only partially capture closed‑loop dynamics, indicating that standard imitation learning does not reliably produce policies that contract errors when perturbed.
arXiv:2608. 10634v1 Announce Type: new Abstract: Model-based reinforcement learning (MBRL), which learns environment dynamics to generate synthetic experience, is a promising approach to sample-efficient decision making.