RLang: A Declarative Language for Describing Partial World Knowledge to Reinforcement Learning Agents
Rafael Rodriguez-Sanchez, Benjamin Adin Spiegel, Jennifer Wang, Roma Patel, Stefanie Tellex, George Konidaris
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.
BibTeX
@inproceedings{icml2023_rlangadeclarativ,
title = {RLang: A Declarative Language for Describing Partial World Knowledge to Reinforcement Learning Agents},
author = {Rafael Rodriguez-Sanchez and Benjamin Adin Spiegel and Jennifer Wang and Roma Patel and Stefanie Tellex and George Konidaris},
booktitle = {ICML 2023},
year = {2023}
}