Learning to Plan from Random Exploration
arXiv:2609.38383v1 Announce Type: cross Abstract: Random exploration reveals how an environment can be traversed before a goal is specified. Can this experience support long-range planning without po...
The paper presents a deep active inference framework for real‑world robotic navigation that combines a diffusion policy with a multiple‑timescale recurrent state‑space model. The diffusion policy generates diverse candidate actions, while the state‑space model predicts long‑horizon outcomes, allowing the system to select actions that minimize expected free energy. Experiments show higher success rates and fewer collisions, especially in exploration‑heavy scenarios, demonstrating the effectiveness of this unified exploration and goal‑directed approach.
arXiv:2609.38383v1 Announce Type: cross Abstract: Random exploration reveals how an environment can be traversed before a goal is specified. Can this experience support long-range planning without po...
Elastic-WAM introduces an adaptive approach to world-action model refinement, allocating computational effort across time and space based on a learned spatiotemporal demand field. This field determines when to stop refinement, how far to advance each denoising step, and which future regions to refresh, allowing the model to tailor refinement depth to specific tasks and states. Experiments on simulation and real‑world long‑horizon manipulation tasks show that Elastic‑WAM achieves state‑of‑the‑art control performance while reducing inference latency.
Elastic-WAM introduces an adaptive spatiotemporal refinement strategy for world-action models, allocating computational effort across time and space based on a learned refinement demand field. This field determines when to stop refinement, how far to advance denoising steps, and which future regions to refresh, enabling efficient recurrent sparse refinement. Experiments on simulation and real‑world long‑horizon manipulation tasks show state‑of‑the‑art control performance with lower inference latency.
arXiv:2608. 14466v1 Announce Type: cross Abstract: An autonomous robot efficiently exploring an unknown environment, such as looking for water sources on Mars, faces two simultaneous demands: building an accurate information map while quickly finding the regions of greatest value, and paying for every meter of travel and the cost of every measurement it takes.
Conventional visual navigation policies often struggle with myopic decision-making and mode collapse in complex environments. While world models offer a promising alternative, existing paradigms typically isolate perception, generation, and control, failing to capture their shared spatio-temporal dynamics.
arXiv:2608. 09876v1 Announce Type: cross Abstract: Physically consistent motion planning remains a fundamental challenge in embodied AI, as generated trajectories must strictly conform to real-world execution dynamics.
arXiv:2603. 02650v2 Announce Type: replace-cross Abstract: Diffusion planners are a strong approach for offline reinforcement learning, but they can fail when value-guided selection favours trajectories that score well yet are locally inconsistent with the environment dynamics, resulting in brittle execution.
The survey "World-Action Models for Robot Learning and Control" reviews recent advances in coupling future world prediction with executable action generation for robots in open environments. It clarifies the scope of World-Action Models (WAMs) relative to conventional world models, model-based RL, and Vision‑Language‑Action policies, and organizes existing methods through a unified taxonomy covering representations, transition modeling, action interfaces, architectures, training pipelines, data modalities, and scaling strategies. The paper also surveys applications in manipulation, navigation, and autonomous driving, summarizes datasets, benchmarks, and metrics, and discusses key challenges such as action alignment, spatial consistency, long‑horizon memory, and efficient inference.
The paper introduces Spatially Aware World Action Model (SA‑WAM), a diffusion‑based framework that extends existing World Action Models by incorporating depth information alongside RGB to enable 3‑D‑aware action and future‑state prediction. SA‑WAM repurposes a pretrained video diffusion model, using a nonlinear encoding to map unbounded depth into the tokenizer’s bounded domain, thus preserving pretrained visual priors without 3‑D‑specific fine‑tuning. The model achieves state‑of‑the‑art performance on RoboCasa and LIBERO‑Plus benchmarks and demonstrates superior real‑world performance on a UR5 robotic arm in randomized environments, while also providing analysis linking world‑model prediction quality to rollout success.
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:2607. 17574v1 Announce Type: cross Abstract: Reinforcement-learning navigation policies for legged robots select actions reactively from current observations and short-term memory, with limited capacity to anticipate how moving obstacles will evolve in the near future.
Exploration in physical control environments requires agents to identify actions whose consequences reveal previously unexplored aspects of the underlying dynamics. However, many intrinsic motivation...