MBRL-Lib: A Modular Library for Model-based Reinforcement Learning
arXiv:2104.10159
Abstract
Model-based reinforcement learning is a compelling framework for data-efficient learning of agents that interact with the world. This family of algorithms has many subcomponents that need to be carefully selected and tuned. As a result the entry-bar for researchers to approach the field and to deploy it in real-world tasks can be daunting. In this paper, we present MBRL-Lib -- a machine learning library for model-based reinforcement learning in continuous state-action spaces based on PyTorch. MBRL-Lib is designed as a platform for both researchers, to easily develop, debug and compare new algorithms, and non-expert user, to lower the entry-bar of deploying state-of-the-art algorithms. MBRL-Lib is open-source at https://github.com/facebookresearch/mbrl-lib.
References in corpus (9)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- The NumPy array: a structure for efficient numerical computation
- Benchmarking Model-Based Reinforcement Learning
- dm_control: Software and Tasks for Continuous Control
- Learning model-based planning from scratch
- Exploring Model-based Planning with Policy Networks
- On the role of planning in model-based deep reinforcement learning
- Imagined Value Gradients: Model-Based Policy Optimization with Transferable Latent Dynamics Models
- Bellman: A Toolbox for Model-Based Reinforcement Learning in TensorFlow