RLang: A Declarative Language for Describing Partial World Knowledge to Reinforcement Learning Agents
Abstract
We introduce RLang, a domain-specific language (DSL) for communicating domain knowledge to an RL agent. Unlike existing RL DSLs that ground to $\textit{single}$ elements of a decision-making formalism (e.g., the reward function or policy), RLang can specify information about every element of a Markov decision process. We define precise syntax and grounding semantics for RLang, and provide a parser that grounds RLang programs to an algorithm-agnostic $\textit{partial}$ world model and policy that can be exploited by an RL agent. We provide a series of example RLang programs demonstrating how different RL methods can exploit the resulting knowledge, encompassing model-free and model-based tabular algorithms, policy gradient and value-based methods, hierarchical approaches, and deep methods.
Cite
Text
Rodriguez-Sanchez et al. "RLang: A Declarative Language for Describing Partial World Knowledge to Reinforcement Learning Agents." International Conference on Machine Learning, 2023.Markdown
[Rodriguez-Sanchez et al. "RLang: A Declarative Language for Describing Partial World Knowledge to Reinforcement Learning Agents." International Conference on Machine Learning, 2023.](https://mlanthology.org/icml/2023/rodriguezsanchez2023icml-rlang/)BibTeX
@inproceedings{rodriguezsanchez2023icml-rlang,
title = {{RLang: A Declarative Language for Describing Partial World Knowledge to Reinforcement Learning Agents}},
author = {Rodriguez-Sanchez, Rafael and Spiegel, Benjamin Adin and Wang, Jennifer and Patel, Roma and Tellex, Stefanie and Konidaris, George},
booktitle = {International Conference on Machine Learning},
year = {2023},
pages = {29161-29178},
volume = {202},
url = {https://mlanthology.org/icml/2023/rodriguezsanchez2023icml-rlang/}
}