arXiv:2606.20627v2 Announce Type: replace Abstract: Joint-Embedding Predictive Architectures (JEPAs) enable agents to plan in latent space by imagining the outcomes of candidate actions, yet task spe...
The paper introduces Hindsight Inverse JEPA Planning (HIJP), a search‑free framework that replaces costly online action sequence optimization with a goal‑conditioned inverse model. HIJP trains by relabeling future observations as goals, providing action supervision across multiple horizons and shaping visual representations. The method also aligns predicted actions with a latent predictor model to enforce action‑transition consistency, achieving high success rates and significant speedups on visual control tasks.
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.
The paper introduces the Dual-Latent World Model (Dual-WM), which separates local execution and long-range planning into distinct latent spaces and dynamics models. A new learning method, Long-Horizon Representation Learning with Weighted Rollout (LoRe), supervises predictions at both levels using exponential horizon weights. Experiments on five goal-conditioned visual control tasks show that Dual-WM improves success rates over strong baselines, especially at longer horizons.
arXiv:2606. 05555v1 Announce Type: new Abstract: Scaling reinforcement learning (RL) to diverse multitask settings remains a central challenge.
arXiv:2603.02935v2 Announce Type: replace Abstract: Offline meta-reinforcement learning seeks to learn a policy that generalizes to new related tasks online. Context-based methods infer a task repres...
Scaling reinforcement learning (RL) to diverse multitask settings remains a central challenge. While recent advances in model-based RL achieve strong performance, they rely on planning and complex training pipelines, making it unclear which components are essential for scalability.
arXiv:2610.27280v1 Announce Type: cross Abstract: Offline goal-conditioned reinforcement learning enables skill acquisition by reaching any goal from any state without dense rewards. Model-based meth...
arXiv:2604. 03208v2 Announce Type: replace Abstract: World models are a promising path to zero-shot embodied control through planning.
arXiv:2501. 14622v5 Announce Type: replace Abstract: Learning efficient representations for decision-making policies is a challenge in imitation learning (IL).
arXiv:2610.22825v1 Announce Type: new Abstract: World models have shown considerable promise in sequential decision-making by anticipating the consequences of actions and providing predictive foresig...
arXiv:2609.31868v2 Announce Type: replace Abstract: Model-predictive control with Joint-Embedding Predictive Architectures (JEPAs) provides a strong zero-shot goal-reaching planner, but it is only ef...