activity
20132026
most citedProgrammatically Interpretable Reinforcement Learning

94 citations · 449 across the 53 of their papers we have counts for

collaborators
Showing 2021Show all

6 papers · 1 filter

cs.LG2021

Neural Program Generation Modulo Static Analysis

Rohan Mukherjee, Yeming Wen, Dipak Chaudhari +3

State-of-the-art neural models of source code tend to be evaluated on the generation of individual expressions and lines of code, and commonly fail on long-horizon tasks such as th…

cs.LG2021★ 1 cited

Unsupervised Learning of Neurosymbolic Encoders

Eric Zhan, Jennifer J. Sun, Ann Kennedy +2

We present a framework for the unsupervised learning of neurosymbolic encoders, which are encoders obtained by composing neural networks with symbolic programs from a domain-specif…

cs.PL2021

Bottom-up Synthesis of Recursive Functional Programs using Angelic Execution

Anders Miltner, Adrian Trejo Nuñez, Ana Brendel +2

We present a novel bottom-up method for the synthesis of functional recursive programs. While bottom-up synthesis techniques can work better than top-down methods in certain settin…

cs.LG2021★ 9 cited

Interpreting Expert Annotation Differences in Animal Behavior

Megan Tjandrasuwita, Jennifer J. Sun, Ann Kennedy +2

Hand-annotated data can vary due to factors such as subjective differences, intra-rater variability, and differing annotator expertise. We study annotations from different experts…

cs.RO2021

OneVision: Centralized to Distributed Controller Synthesis with Delay Compensation

Jiayi Wei, Tongrui Li, Swarat Chaudhuri +2

We propose a new algorithm to simplify the controller development for distributed robotic systems subject to external observations, disturbances, and communication delays. Unlike p…

cs.CL2021

Flexible Generation of Natural Language Deductions

Kaj Bostrom, Xinyu Zhao, Swarat Chaudhuri +1

An interpretable system for open-domain reasoning needs to express its reasoning process in a transparent form. Natural language is an attractive representation for this purpose --…