arXiv:2609.17325v1 Announce Type: new Abstract: Biological cells can be viewed as individual, interacting agents whose collective dynamics give rise to adaptive behaviour at multiple levels of organi...
arXiv:2606. 19990v1 Announce Type: new Abstract: While RL has become a promising tool for refining world models, existing methods largely rely on conservative rollouts near the training distribution, limiting exploration, behavioral diversity, and richer dynamic discovery.
The paper introduces Hamiltonian Temporal Contrastive Curiosity (HTC²), a method that combines multi‑horizon temporal representation learning with Hamiltonian phase‑space structure to guide exploration in physical control environments. HTC² uses a horizon‑conditioned contrastive critic to learn relationships between future state pairs within an episode, and the resulting representation distance serves as an intrinsic reward. The reward is further modulated by bounded multi‑step Hamiltonian variation, and the framework is integrated with Soft Actor‑Critic and Proximal Policy Optimization, evaluated on six DeepMind Control Suite tasks against several baseline curiosity methods.
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.
Exploration in physical control environments requires agents to identify actions whose consequences reveal previously unexplored aspects of the underlying dynamics. However, many intrinsic motivation...
arXiv:2605.14211v4 Announce Type: replace Abstract: Long-horizon visuomotor tasks remain a fundamental challenge in AI, as current methods rely on hand-engineered rewards or action-labeled demonstrat...
arXiv:2606. 19476v1 Announce Type: cross Abstract: Effective machine learning depends not only on how we model data, but also on what data we choose to collect.
The paper introduces a neurosymbolic world model that separates observation reconstruction from reward prediction, enabling the model to adapt zero‑shot to new reward functions defined over a shared symbolic state space. This approach addresses the task‑dependency of traditional neural world models, which learn latent representations tied to specific training tasks. Experiments show that the neurosymbolic formulation generalises more strongly than purely neural methods.
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 study investigates how intrinsic motivation drives autonomous behavior in fruit flies by combining whole-brain recordings with a neuromechanical digital twin. It shows that a hierarchical policy selecting from low‑level motor primitives, trained with 20 intrinsic motivation algorithms, can reproduce fly locomotor statistics and internal representations of future actions. The DIAYN algorithm, which maximizes behavioral entropy and sensory separability, best matches fly behavior and neural coding, capturing individual variability and interhemispheric kinematic encoding.
arXiv:2605. 14211v3 Announce Type: replace Abstract: Long-horizon embodied tasks remain a fundamental challenge in AI, as current methods rely on hand-engineered rewards or action-labeled demonstrations, neither of which scales.
arXiv:2609.38334v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as agents for multi-step decision-making, yet transfer poorly to unseen environments. World-mode...