A Composable Specification Language for Reinforcement Learning Tasks

2020-08-21 · NeurIPS 2019 12 · Kishor Jothimurugan, Rajeev Alur, Osbert Bastani

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 SPECTRL, and show that it outperforms several state-of-the-art baselines.

📄 PDF Abstract BibTeX arXiv:2008.09293

Code (1)

keyshor/spectrl_tool 공식 구현 pytorch

Tasks

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

ComposableNav: Instruction-Following Navigation in Dynamic Environments via Composable Diffusion

2025-09-22 · Zichao Hu, Chen Tang, Michael J. Munje, Yifeng Zhu 외 arxiv

This paper considers the problem of enabling robots to navigate dynamic environments while following instructions. The challenge lies in the combinatorial nature of instruction specifications: each instruction can includ…

Reinforcement Learning

A Visual Language for Composable Inductive Programming

2020-09-18 · Edward McDaid, Sarah McDaid

We present Zoea Visual which is a visual programming language based on the Zoea composable inductive programming language. Zoea Visual allows users to create software directly from a specification that resembles a set of…

Hierarchical Reinforcement Learning for Concurrent Discovery of Compound and Composable Policies

2019-05-23 · Domingo Esteban, Leonel Rozo, Darwin G. Caldwell

A common strategy to deal with the expensive reinforcement learning (RL) of complex tasks is to decompose them into a collection of subtasks that are usually simpler to learn as well as reusable for new problems. However…

Hierarchical Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Zoea -- Composable Inductive Programming Without Limits

2019-11-13 · Edward McDaid, Sarah McDaid

Automatic generation of software from some form of specification has been a long standing goal of computer science research. To date successful results have been reported for the production of relatively small programs. …

Form

Modeling Unseen Environments with Language-guided Composable Causal Components in Reinforcement Learning

2025-05-13 · Xinyue Wang, Biwei Huang

Generalization in reinforcement learning (RL) remains a significant challenge, especially when agents encounter novel environments with unseen dynamics. Drawing inspiration from human compositional reasoning -- where kno…

Meta-Learning Reinforcement Learning (RL)Representation Learning