Search Results for author:
Found 25 papers, 12 papers with code
Policy Optimization with Robustness Certificates
This signal is used to guide policy learning, and the abstract interpretation used to construct it directly leads to the robustness certificate returned at convergence.
Natural Language Deduction with Incomplete Information
A growing body of work studies how to answer a question or verify a claim by generating a natural language "proof": a chain of deductive inferences yielding the answer based on a set of premises.
Neurosymbolic Programming for Science
Neurosymbolic Programming (NP) techniques have the potential to accelerate scientific discovery.
Guiding Safe Exploration with Weakest Preconditions
In reinforcement learning for safety-critical settings, it is often desirable for the agent to obey safety constraints at all points in time, including during training.
Policy Optimization with Linear Temporal Logic Constraints
We study the problem of policy optimization (PO) with linear temporal logic (LTL) constraints.
Safe Neurosymbolic Learning with Differentiable Symbolic Execution
We study the problem of learning worst-case-safe parameters for programs that use neural networks as well as symbolic, human-written code.
Natural Language Deduction through Search over Statement Compositions
In settings from fact-checking to question answering, we frequently want to know whether a collection of evidence (premises) entails a hypothesis.
Neural Program Generation Modulo Static Analysis
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 the generation of entire method bodies.
Unsupervised Learning of Neurosymbolic Encoders
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-specific language.
Interpreting Expert Annotation Differences in Animal Behavior
Hand-annotated data can vary due to factors such as subjective differences, intra-rater variability, and differing annotator expertise.
Flexible Generation of Natural Language Deductions
Natural language is an attractive representation for this purpose -- it is both highly expressive and easy for humans to understand.
Few-shot Image Classification: Just Use a Library of Pre-trained Feature Extractors and a Simple Classifier
Recent papers have suggested that transfer learning can outperform sophisticated meta-learning methods for few-shot image classification.
Neurosymbolic Reinforcement Learning with Formally Verified Exploration
We present Revel, a partially neural reinforcement learning (RL) framework for provably safe exploration in continuous state and action spaces.
Learning Differentiable Programs with Admissible Neural Heuristics
This relaxed program is differentiable and can be trained end-to-end, and the resulting training loss is an approximately admissible heuristic that can guide the combinatorial search.
Meta-Meta Classification for One-Shot Learning
We present a new approach, called meta-meta classification, to learning in small-data settings.
Imitation-Projected Programmatic Reinforcement Learning
First, we view our learning task as optimization in policy space, modulo the constraint that the desired policy has a programmatic representation, and solve this optimization problem using a form of mirror descent that takes a gradient step into the unconstrained policy space and then projects back onto the constrained space.
Control Regularization for Reduced Variance Reinforcement Learning
We show that functional regularization yields a bias-variance trade-off, and propose an adaptive tuning strategy to optimize this trade-off.
Finite Automata Can be Linearly Decoded from Language-Recognizing RNNs
We study the internal representations that a recurrent neural network (RNN) uses while learning to recognize a regular formal language.
Optimization and Abstraction: A Synergistic Approach for Analyzing Neural Network Robustness
In recent years, the notion of local robustness (or robustness for short) has emerged as a desirable property of deep neural networks.
Representing Formal Languages: A Comparison Between Finite Automata and Recurrent Neural Networks
We investigate the internal representations that a recurrent neural network (RNN) uses while learning to recognize a regular formal language.
Programmatically Interpretable Reinforcement Learning
Unlike the popular Deep Reinforcement Learning (DRL) paradigm, which represents policies by neural networks, PIRL represents policies using a high-level, domain-specific programming language.
HOUDINI: Lifelong Learning as Program Synthesis
We present a neurosymbolic framework for the lifelong learning of algorithmic tasks that mix perception and procedural reasoning.
Bounded Policy Synthesis for POMDPs with Safe-Reachability Objectives
In this work, we study POMDPs with safe-reachability objectives, which require that with a probability above some threshold, a goal state is eventually reached while keeping the probability of visiting unsafe states below some threshold.
Neural Attribute Machines for Program Generation
During generation, NAMs make significantly fewer violations of the constraints of the underlying grammar than RNNs trained only on samples from the language of the grammar.
Neural Sketch Learning for Conditional Program Generation
We study the problem of generating source code in a strongly typed, Java-like programming language, given a label (for example a set of API calls or types) carrying a small amount of information about the code that is desired.
