arXiv Machine Learning
Linear Recurrent Memory Suffices to Distil a World-Model Policy for Robot Air Hockey
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Sep 24
MemBodied: Recurrent Associative Memory for Vision-Language-Action Models
MemBodied introduces a fixed‑size episodic memory for Vision‑Language‑Action models, comprising an associative state that tracks interactions across policy calls and an episode anchor that stores a compact representation of the initial scene. By conditioning action generation on these memory components instead of raw past observations, MemBodied reduces context bloat and inference latency. In five memory‑dependent RMBench tasks, it outperforms stateless and vanilla recurrent policies by significant margins, and achieves a 90.6% success rate on the LIBERO‑Long suite, improving over the baseline by 5.4%.
arXiv AI
Jul 24
VPWEM: Non-Markovian Visuomotor Policy with Working and Episodic Memory
arXiv:2603. 04910v2 Announce Type: replace-cross Abstract: Imitation learning from human demonstrations has achieved significant success in robotic control, yet most visuomotor policies still condition on single-step observations or short-context histories, making them struggle with non-Markovian tasks that require long-term memory.
arXiv Machine Learning
Jul 16
Pretraining in Actor-Critic Reinforcement Learning for Locomotion
arXiv:2510. 12363v4 Announce Type: replace-cross Abstract: The pretraining-finetuning paradigm has facilitated numerous transformative advancements in artificial intelligence research in recent years.
arXiv Machine Learning
Sep 16
Robust Recurrent Reinforcement Learning under Evolving Hidden Disturbances with Application to Rover Wheel Slip
The paper studies recurrent Twin Delayed Deep Deterministic Policy Gradient (TD3) agents in environments with evolving hidden disturbances, focusing on how observation history, action history, history length, and network structure influence performance. Three recurrent architectures are compared under controlled disturbances, revealing that action history is crucial when responses depend on prior actions and that a unified temporal sequence of action-observation pairs outperforms separate branches. The authors introduce H‑TD3, which reuses actor-generated recurrent states to initialize the critic, and demonstrate that these architectures excel in a rover wheel‑slip simulation, with policies trained on temporally structured disturbances transferring better to unseen slip dynamics.
arXiv Machine Learning
Jul 1
Machine Learning-based Feedback Linearization Control of Quadrotor Subject to Unmodeled Dynamics
arXiv:2606. 31199v1 Announce Type: cross Abstract: The control of agile quadrotors in dynamic and uncertain environments remains an open area of investigation to this day, particularly when the complete system dynamics are partially known or highly nonlinear.
arXiv AI
Jun 11
Implicit Neural Representations of Individual Behavior
arXiv:2606. 12200v1 Announce Type: cross Abstract: We study policy representation learning from unlabeled multi-policy behavioral data.