Skip to main content
Search

# Partially Observable Markov Decision Process

2 related articles

Subscribe to updates
  1. arXiv

    Recurrent memory no longer needs training: frozen networks recall over 256 steps with half the trainable parameters

    In partially observable reinforcement learning, freezing the recurrent memory module and training only the output and mixer layers still matches fully trained counterparts on delayed recall, discrete and continuous control, and pixel-based tasks, while cutting trainable parameters by more than half.

  2. arXiv

    Modeling pedestrian crossing as a POMDP with perceptual, cognitive, and motor constraints and training it with deep RL reproduces the broadest range of empirical crossing behaviors

    The work defines pedestrian-vehicle interaction as a partially observable Markov decision process (POMDP) with theory-grounded perceptual, cognitive, and motor constraints, trains it in a simulator via deep reinforcement learning with domain randomization, and shows that the learned policies produce human-like behavior in complex scenarios including multiple lanes, heavy traffic, and dangerous driving styles, reproducing the broadest range of empirical findings on human crossing behavior so far, including gap acceptance, yielding acceptance, hesitation, and evasive speed adjustment; the learned policies also transfer to unseen traffic environments and can be adapted to local traffic norms with finetuning.

You’re all caught up