mbbl | Arxiv Link PDF Project Page Abstract | Machine Learning library

mbbl is a Python library typically used in Artificial Intelligence, Machine Learning, Deep Learning, Pytorch applications. mbbl has no vulnerabilities, it has build file available and it has low support. However mbbl has 11 bugs. You can download it from GitHub.

Arxiv Link PDF Project Page Abstract: Model-based reinforcement learning (MBRL) is widely seen as having the potential to be significantly more sample efficient than model-free RL. However, research in model-based RL has not been very standardized. It is fairly common for authors to experiment with self-designed environments, and there are several separate lines of research, which are sometimes closed-sourced or not reproducible. Accordingly, it is an open question how these various existing MBRL algorithms perform relative to each other. To facilitate research in MBRL, in this paper we gather a wide collection of MBRL algorithms and propose over 18 benchmarking environments specially designed for MBRL. We benchmark these MBRL algorithms with unified problem settings, including noisy environments. Beyond cataloguing performance, we explore and unify the underlying algorithmic differences across MBRL algorithms. We characterize three key research challenges for future MBRL research: the dynamics coupling effect, the planning horizon dilemma, and the early-termination dilemma.