资源论文A Composable Specification Language for Reinforcement Learning Tasks

A Composable Specification Language for Reinforcement Learning Tasks

2020-02-26 | |  239 |   82 |   0

Abstract

Reinforcement learning is a promising approach for learning control policies for robot tasks. However, specifying complex tasks (e.g., with multiple objectives and safety constraints) can be challenging, since the user must design a reward function that encodes the entire task. Furthermore, the user often needs to manually shape the reward to ensure convergence of the learning algorithm. We propose a language for specifying complex control tasks, along with an algorithm that compiles specifications in our language into a reward function and automatically performs reward shaping. We implement our approach in a tool called S PECTRL, and show that it outperforms several state-of-the-art baselines.

上一篇:Unsupervised Co-Learning on G-Manifolds Across Irreducible Representations

下一篇:Language as an Abstraction for Hierarchical Deep Reinforcement Learning

用户评价
全部评价

热门资源

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Hierarchical Task...

    We extend hierarchical task network planning wi...

  • Shape-based Autom...

    We present an algorithm for automatic detection...