# RLang: A Declarative Language for Describing Partial World Knowledge to Reinforcement Learning Agents

arXiv: https://arxiv.org/abs/2208.06448 · HTML: https://mlsanity.com/paper/2208.06448/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 42 references that are in the map.
- First posted on arXiv 12 Aug 2022.

## Builds on (most cited first, 15 of 15)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Deep Reinforcement Learning with Double Q-learning](https://mlsanity.com/paper/1509.06461/) (2015)
- [Modular Multitask Reinforcement Learning with Policy Sketches](https://mlsanity.com/paper/1611.01796/) (2016)
- [A Survey of Reinforcement Learning Informed by Natural Language](https://mlsanity.com/paper/1906.03926/) (2019)
- [Using Natural Language for Reward Shaping in Reinforcement Learning](https://mlsanity.com/paper/1903.02020/) (2019)
- [Mapping Instructions and Visual Observations to Actions with Reinforcement Learning](https://mlsanity.com/paper/1704.08795/) (2017)
- [Learning to Understand Goal Specifications by Modelling Reward](https://mlsanity.com/paper/1806.01946/) (2018)
- [A Composable Specification Language for Reinforcement Learning Tasks](https://mlsanity.com/paper/2008.09293/) (2020)
- [Environment-Independent Task Specifications via GLTL](https://mlsanity.com/paper/1704.04341/) (2017)
- [ChainerRL: A Deep Reinforcement Learning Library](https://mlsanity.com/paper/1912.03905/) (2019)
- [Learning Rewards from Linguistic Feedback](https://mlsanity.com/paper/2009.14715/) (2020)
- [Learning to Win by Reading Manuals in a Monte-Carlo Framework](https://mlsanity.com/paper/1401.5390/) (2014)
- [RTFM: Generalising to Novel Environment Dynamics via Reading](https://mlsanity.com/paper/1910.08210/) (2019)
- [PixL2R: Guiding Reinforcement Learning Using Natural Language by Mapping Pixels to Rewards](https://mlsanity.com/paper/2007.15543/) (2020)
- [Programmable Agents](https://mlsanity.com/paper/1706.06383/) (2017)

## Built on by (most cited first, 4 of 4)

- [A Survey of Robotic Language Grounding: Tradeoffs between Symbols and Embeddings](https://mlsanity.com/paper/2405.13245/) (2024)
- [Reinforcement Learning with Physics-Informed Symbolic Program Priors for Zero-Shot Wireless Indoor Navigation](https://mlsanity.com/paper/2506.22365/) (2025)
- [A Research Agenda for Usability and Generalisation in Reinforcement Learning](https://mlsanity.com/paper/2412.16970/) (2024)
- [LLM-Guided Contextual Action Evaluation for Operational Decisions in Industrial Processes](https://mlsanity.com/paper/2608.24156/) (2026)

## Abstract (arXiv)

We introduce RLang, a domain-specific language (DSL) for communicating domain knowledge to an RL agent. Unlike existing RL DSLs that ground to textitsingle 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 textitpartial 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.