babble: Learning Better Abstractions with E-Graphs and Anti-unification

Cao, David; Kunkel, Rose; Nandi, Chandrakana; Willsey, Max; Tatlock, Zachary; Polikarpova, Nadia

doi:10.1145/3571207

Cited by 17 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As the number of possible refactorings grows combinatorially with program size, we needed a new data structure for representing and manipulating sets of refactorings, which we designed by combining ideas from version space algebras [20][21][22] and equivalence graphs [23] (described in our companion manuscript [2]). Recent work improved upon our original refactoring algorithm by making it more expressive [24] as well as orders of magnitude faster [25].…”

Section: Wake/sleep Program Learningmentioning

confidence: 99%

DreamCoder: growing generalizable, interpretable knowledge with wake–sleep Bayesian program learning

Ellis

Wong

Nye

et al. 2023

Phil. Trans. R. Soc. A.

View full text Add to dashboard Cite

Expert problem-solving is driven by powerful languages for thinking about problems and their solutions. Acquiring expertise means learning these languages—systems of concepts, alongside the skills to use them. We present DreamCoder, a system that learns to solve problems by writing programs. It builds expertise by creating domain-specific programming languages for expressing domain concepts, together with neural networks to guide the search for programs within these languages. A ‘wake–sleep’ learning algorithm alternately extends the language with new symbolic abstractions and trains the neural network on imagined and replayed problems. DreamCoder solves both classic inductive programming tasks and creative tasks such as drawing pictures and building scenes. It rediscovers the basics of modern functional programming, vector algebra and classical physics, including Newton’s and Coulomb’s laws. Concepts are built compositionally from those learned earlier, yielding multilayered symbolic representations that are interpretable and transferrable to new tasks, while still growing scalably and flexibly with experience. This article is part of a discussion meeting issue ‘Cognitive artificial intelligence’.

show abstract

Section: Wake/sleep Program Learningmentioning

confidence: 99%

DreamCoder: growing generalizable, interpretable knowledge with wake–sleep Bayesian program learning

Ellis

Wong

Nye

et al. 2023

Phil. Trans. R. Soc. A.

View full text Add to dashboard Cite

show abstract

“…Another promising method is learning a library of functions from previously solved problems. These functions are then reusable in an updated domain-specific language to solve more challenging problems (Hewitt, Le, and Tenenbaum 2020;Ellis et al 2021Ellis et al , 2018Cao et al 2023;Bowers et al 2023).…”

Section: Related Workmentioning

confidence: 99%

Learning of Generalizable and Interpretable Knowledge in Grid-Based Reinforcement Learning Environments

Eberhardinger,

Maucher,

Maghsudi

2023

AIIDE

View full text Add to dashboard Cite

Understanding the interactions of agents trained with deep reinforcement learning is crucial for deploying agents in games or the real world. In the former, unreasonable actions confuse players. In the latter, that effect is even more significant, as unexpected behavior cause accidents with potentially grave and long-lasting consequences for the involved individuals. In this work, we propose using program synthesis to imitate reinforcement learning policies after seeing a trajectory of the action sequence. Programs have the advantage that they are inherently interpretable and verifiable for correctness. We adapt the state-of-the-art program synthesis system DreamCoder for learning concepts in grid-based environments, specifically, a navigation task and two miniature versions of Atari games, Space Invaders and Asterix. By inspecting the generated libraries, we can make inferences about the concepts the black-box agent has learned and better understand the agent's behavior. We achieve the same by visualizing the agent's decision-making process for the imitated sequences. We evaluate our approach with different types of program synthesizers based on a search-only method, a neural-guided search, and a language model fine-tuned on code.

show abstract

“…We build WASM-MUTATE on top of e-graphs [9]. An e-graph is a graph data structure utilized for representing rewriting rules and their chaining.…”

Section: E-graphs For Webassemblymentioning

confidence: 99%

Wasm-Mutate: Fast and Effective Binary Diversification for Webassembly

Cabrera Arteaga,

Fitzgerald,

Monperrus

et al. 2023

Preprint

View full text Add to dashboard Cite

babble: Learning Better Abstractions with E-Graphs and Anti-unification

Cited by 17 publications

References 22 publications

DreamCoder: growing generalizable, interpretable knowledge with wake–sleep Bayesian program learning

DreamCoder: growing generalizable, interpretable knowledge with wake–sleep Bayesian program learning

Learning of Generalizable and Interpretable Knowledge in Grid-Based Reinforcement Learning Environments

Wasm-Mutate: Fast and Effective Binary Diversification for Webassembly

Contact Info

Product

Resources

About