Jul 2026
P3: Probabilistic Policy Propagation for Stable VAE-Based Robot Learning
Variational Autoencoders are widely used to encode high-dimensional and noisy observations in robotics. However, their stochastic latent creates a mismatch with Proximal Policy Optimization (PPO): an effective policy marginalizes over the latent distribution, whereas former implementations estimate its probability rati...
Li-Yun Yan, Jian-Ming Ma, Yang Zhang et al.
· arXiv.org · 0 citations