Timezone: »

 
Poster
RLang: A Declarative Language for Describing Partial World Knowledge to Reinforcement Learning Agents
Rafael A Rodriguez-Sanchez · Benjamin Spiegel · Jennifer Wang · Roma Patel · Stefanie Tellex · George Konidaris

Tue Jul 25 02:00 PM -- 04:30 PM (PDT) @ Exhibit Hall 1 #615
in Poster Session 1 »
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.
[ PDF]  [ Poster] 

Author Information

Rafael A Rodriguez-Sanchez (Brown University)
Benjamin Spiegel (Brown University)
Jennifer Wang (Brown University)
Roma Patel (DeepMind)
Stefanie Tellex (, Brown University)
George Konidaris (Brown)

More from the Same Authors