# Target Languages (vs. Inductive Biases) for Learning to Act and Plan

arXiv: https://arxiv.org/abs/2109.07195 · HTML: https://mlsanity.com/paper/2109.07195/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 70 references that are in the map.
- First posted on arXiv 15 Sep 2021.

## Builds on (most cited first, 26 of 26)

- [Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges](https://mlsanity.com/paper/2104.13478/) (2021)
- [Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm](https://mlsanity.com/paper/1712.01815/) (2017)
- [Inductive Biases for Deep Learning of Higher-Level Cognition](https://mlsanity.com/paper/2011.15091/) (2020)
- [BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning](https://mlsanity.com/paper/1810.08272/) (2018)
- [Recurrent Independent Mechanisms](https://mlsanity.com/paper/1909.10893/) (2019)
- [Deep Learning: A Critical Appraisal](https://mlsanity.com/paper/1801.00631/) (2018)
- [Towards Causal Representation Learning](https://mlsanity.com/paper/2102.11107/) (2021)
- [Building machines that adapt and compute like brains](https://mlsanity.com/paper/1711.04203/) (2017)
- [The Logic of Graph Neural Networks](https://mlsanity.com/paper/2104.14624/) (2021)
- [Neural Production Systems: Learning Rule-Governed Visual Dynamics](https://mlsanity.com/paper/2103.01937/) (2021)
- [Foundations for Restraining Bolts: Reinforcement Learning with LTLf/LDLf restraining specifications](https://mlsanity.com/paper/1807.06333/) (2018)
- [Thinking Fast and Slow: Optimization Decomposition Across Timescales](https://mlsanity.com/paper/1704.07785/) (2017)
- [Linguistic generalization and compositionality in modern artificial neural networks](https://mlsanity.com/paper/1904.00157/) (2019)
- [Human-Level Reinforcement Learning through Theory-Based Modeling, Exploration, and Planning](https://mlsanity.com/paper/2107.12544/) (2021)
- [ASNets: Deep Learning for Generalised Planning](https://mlsanity.com/paper/1908.01362/) (2019)
- [Learning First-Order Symbolic Representations for Planning from the Structure of the State Space](https://mlsanity.com/paper/1909.05546/) (2019)
- [What Can Learned Intrinsic Rewards Capture?](https://mlsanity.com/paper/1912.05500/) (2019)
- [An Explicitly Relational Neural Network Architecture](https://mlsanity.com/paper/1905.10307/) (2019)
- [Few-Shot Bayesian Imitation Learning with Logical Program Policies](https://mlsanity.com/paper/1904.06317/) (2019)
- [Features, Projections, and Representation Change for Generalized Planning](https://mlsanity.com/paper/1801.10055/) (2018)
- [Unsupervised Grounding of Plannable First-Order Logic Representation from Images](https://mlsanity.com/paper/1902.08093/) (2019)
- [Learning First-Order Representations for Planning from Black-Box States: New Results](https://mlsanity.com/paper/2105.10830/) (2021)
- [Model-free, Model-based, and General Intelligence](https://mlsanity.com/paper/1806.02308/) (2018)
- [Expressing and Exploiting the Common Subgoal Structure of Classical Planning Domains Using Sketches: Extended Version](https://mlsanity.com/paper/2105.04250/) (2021)
- [Human-Level Intelligence or Animal-Like Abilities?](https://mlsanity.com/paper/1707.04327/) (2017)
- [Symbolic Network: Generalized Neural Policies for Relational MDPs](https://mlsanity.com/paper/2002.07375/) (2020)

## Built on by (most cited first, 5 of 5)

- [Current and Future Challenges in Knowledge Representation and Reasoning](https://mlsanity.com/paper/2308.04161/) (2023)
- [Inductive Biases for Zero-shot Systematic Generalization in Language-informed Reinforcement Learning](https://mlsanity.com/paper/2501.15270/) (2025)
- [Language-Based Causal Representation Learning](https://mlsanity.com/paper/2207.05259/) (2022)
- [Synthesis of Procedural Models for Deterministic Transition Systems](https://mlsanity.com/paper/2307.14368/) (2023)
- [CAREL: Instruction-guided reinforcement learning with cross-modal auxiliary objectives](https://mlsanity.com/paper/2411.19787/) (2024)

## Abstract (arXiv)

Recent breakthroughs in AI have shown the remarkable power of deep learning and deep reinforcement learning. These developments, however, have been tied to specific tasks, and progress in out-of-distribution generalization has been limited. While it is assumed that these limitations can be overcome by incorporating suitable inductive biases, the notion of inductive biases itself is often left vague and does not provide meaningful guidance. In the paper, I articulate a different learning approach where representations do not emerge from biases in a neural architecture but are learned over a given target language with a known semantics. The basic ideas are implicit in mainstream AI where representations have been encoded in languages ranging from fragments of first-order logic to probabilistic structural causal models. The challenge is to learn from data the representations that have traditionally been crafted by hand. Generalization is then a result of the semantics of the language. The goals of this paper are to make these ideas explicit, to place them in a broader context where the design of the target language is crucial, and to illustrate them in the context of learning to act and plan. For this, after a general discussion, I consider learning representations of actions, general policies, and subgoals ("intrinsic rewards"). In these cases, learning is formulated as a combinatorial problem but nothing prevents the use of deep learning techniques instead. Indeed, learning representations over languages with a known semantics provides an account of what is to be learned, while learning representations with neural nets provides a complementary account of how representations can be learned. The challenge and the opportunity is to bring the two together.