all AI news
Towards A Unified Policy Abstraction Theory and Representation Learning Approach in Markov Decision Processes. (arXiv:2209.07696v1 [cs.LG])
cs.LG updates on arXiv.org arxiv.org
Lying on the heart of intelligent decision-making systems, how policy is
represented and optimized is a fundamental problem. The root challenge in this
problem is the large scale and the high complexity of policy space, which
exacerbates the difficulty of policy learning especially in real-world
scenarios. Towards a desirable surrogate policy space, recently policy
representation in a low-dimensional latent space has shown its potential in
improving both the evaluation and optimization of policy. The key question
involved in these studies …
arxiv decision markov policy processes representation representation learning theory