ICLR 2023poster17 citations

Safe Reinforcement Learning From Pixels Using a Stochastic Latent Representation

Yannick Hogewind, Thiago D. Simão, Tal Kachman, Nils Jansen

Abstract

We address the problem of safe reinforcement learning from pixel observations. Inherent challenges in such settings are (1) a trade-off between reward optimization and adhering to safety constraints, (2) partial observability, and (3) high-dimensional observations. We formalize the problem in a constrained, partially observable Markov decision process framework, where an agent obtains distinct reward and safety signals. To address the curse of dimensionality, we employ a novel safety critic using the stochastic latent actor-critic (SLAC) approach. The latent variable model predicts rewards and safety violations, and we use the safety critic to train safe policies. Using well-known benchmark environments, we demonstrate competitive performance over existing approaches regarding computational requirements, final reward return, and satisfying the safety constraints.

safetyreinforcement learningsafe reinforcement learningconstrained Markov decision processpartially observable Markov decision processMDPPOMDP
BibTeX
@inproceedings{
hogewind2023safe,
title={Safe Reinforcement Learning From Pixels Using a Stochastic Latent Representation},
author={Yannick Hogewind and Thiago D. Sim{\~a}o and Tal Kachman and Nils Jansen},
booktitle={The Eleventh International Conference on Learning Representations },
year={2023},
url={https://openreview.net/forum?id=b39dQt_uffW}
}
Safe Reinforcement Learning From Pixels Using a Stochastic Latent Representation · ICLR 2023