Search Results for author:
Found 28 papers, 14 papers with code
Natural Language to Code Generation in Interactive Data Science Notebooks
To measure the performance of AI pair programmers that automatically synthesize programs for those tasks given natural language (NL) intents from users, we build ARCADE, a benchmark of 1082 code generation problems using the pandas data analysis framework in data science notebooks.
A Simple, Yet Effective Approach to Finding Biases in Code Generation
This work shows that current code generation systems exhibit undesired biases inherited from their large language model backbones, which can reduce the quality of the generated code under specific circumstances.
Solving Quantitative Reasoning Problems with Language Models
Language models have achieved remarkable performance on a wide range of tasks that require natural language understanding.
Ranked #1 on
Multi-task Language Understanding
on MMLU
(STEM metric)
Multi-Game Decision Transformers
Specifically, we show that a single transformer-based model - with a single set of weights - trained purely offline can play a suite of up to 46 Atari games simultaneously at close-to-human performance.
PaLM: Scaling Language Modeling with Pathways
To further our understanding of the impact of scale on few-shot learning, we trained a 540-billion parameter, densely activated, Transformer language model, which we call Pathways Language Model PaLM.
Ranked #1 on
Common Sense Reasoning
on BIG-bench (Known Unknowns)
Measuring CLEVRness: Blackbox testing of Visual Reasoning Models
Visual question answering provides a convenient framework for testing the model's abilities by interrogating the model through questions about the scene.
Show Your Work: Scratchpads for Intermediate Computation with Language Models
Large pre-trained language models perform remarkably well on tasks that can be done "in one pass", such as generating realistic text or synthesizing computer programs.
Sparse is Enough in Scaling Transformers
We study sparse variants for all layers in the Transformer and propose Scaling Transformers, a family of next generation Transformer models that use sparse layers to scale efficiently and perform unbatched decoding much faster than the standard Transformer as we scale up the model size.
Off-Policy Correction For Multi-Agent Reinforcement Learning
The key advantage of our algorithm is its high scalability in a multi-worker setting.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
Hierarchical Transformers Are More Efficient Language Models
Transformer models yield impressive results on many NLP and sequence modeling tasks.
Ranked #4 on
Image Generation
on ImageNet 32x32
(bpd metric)
Measuring CLEVRness: Black-box Testing of Visual Reasoning Models
To answer such a question, we extend the visual question answering framework and propose the following behavioral test in the form of a two-player game.
Program Synthesis with Large Language Models
Our largest models, even without finetuning on a code dataset, can synthesize solutions to 59. 6 percent of the problems from MBPP using few-shot learning with a well-designed prompt.
Measuring and Improving BERT's Mathematical Abilities by Predicting the Order of Reasoning.
How many fruits do you have in total?
Measuring and Improving BERT's Mathematical Abilities by Predicting the Order of Reasoning
How many fruits do you have in total?
Q-Value Weighted Regression: Reinforcement Learning with Limited Data
QWR is an extension of Advantage Weighted Regression (AWR), an off-policy actor-critic algorithm that performs very well on continuous control tasks, also in the offline setting, but has low sample efficiency and struggles with high-dimensional observation spaces.
CARLA Real Traffic Scenarios -- novel training ground and benchmark for autonomous driving
This work introduces interactive traffic scenarios in the CARLA simulator, which are based on real-world traffic.
Neural heuristics for SAT solving
We use neural graph networks with a message-passing architecture and an attention mechanism to enhance the branching heuristic in two SAT-solving algorithms.
Model Based Reinforcement Learning for Atari
We describe Simulated Policy Learning (SimPLe), a complete model-based deep RL algorithm based on video prediction models and present a comparison of several model architectures, including a novel architecture that yields the best results in our setting.
Simulation-based reinforcement learning for real-world autonomous driving
Using reinforcement learning in simulation and synthetic data is motivated by lowering costs and engineering effort.
Towards Finding Longer Proofs
We present a reinforcement learning (RL) based guidance system for automated theorem proving geared towards Finding Longer Proofs (FLoP).
Model-Based Reinforcement Learning for Atari
We describe Simulated Policy Learning (SimPLe), a complete model-based deep RL algorithm based on video prediction models and present a comparison of several model architectures, including a novel architecture that yields the best results in our setting.
Ranked #8 on
Atari Games 100k
on Atari 100k
Expert-augmented actor-critic for ViZDoom and Montezumas Revenge
We propose an expert-augmented actor-critic algorithm, which we evaluate on two environments with sparse rewards: Montezumas Revenge and a demanding maze from the ViZDoom suite.
Reinforcement Learning of Theorem Proving
The strongest version of the system is trained on a large corpus of mathematical problems and evaluated on previously unseen problems.
Learning to Run challenge solutions: Adapting reinforcement learning methods for neuromusculoskeletal environments
In the NIPS 2017 Learning to Run challenge, participants were tasked with building a controller for a musculoskeletal model to make it run as fast as possible through an obstacle course.
Distributed Deep Reinforcement Learning: Learn how to play Atari games in 21 minutes
We present a study in Distributed Deep Reinforcement Learning (DDRL) focused on scalability of a state-of-the-art Deep Reinforcement Learning algorithm known as Batch Asynchronous Advantage ActorCritic (BA3C).
Ranked #20 on
Atari Games
on Atari 2600 Boxing
Atari games and Intel processors
The asynchronous nature of the state-of-the-art reinforcement learning algorithms such as the Asynchronous Advantage Actor-Critic algorithm, makes them exceptionally suitable for CPU computations.
Learning from the memory of Atari 2600
We train a number of neural networks to play games Bowling, Breakout and Seaquest using information stored in the memory of a video game console Atari 2600.
