Search Results for author: Adam Lerer

Found 32 papers, 17 papers with code

“Other-Play” for Zero-Shot Coordination

no code implementations ICML 2020 Hengyuan Hu, Alexander Peysakhovich, Adam Lerer, Jakob Foerster

We consider the problem of zero-shot coordination - constructing AI agents that can coordinate with novel partners they have not seen before (e. g. humans).

Multi-agent Reinforcement Learning Reinforcement Learning (RL)

Attention Sorting Combats Recency Bias In Long Context Language Models

no code implementations28 Sep 2023 Alexander Peysakhovich, Adam Lerer

Current language models often fail to incorporate long contexts efficiently during generation.

Position Retrieval

Human-AI Coordination via Human-Regularized Search and Learning

no code implementations11 Oct 2022 Hengyuan Hu, David J Wu, Adam Lerer, Jakob Foerster, Noam Brown

First, we show that our method outperforms experts when playing with a group of diverse human players in ad-hoc teams.

Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning

1 code implementation11 Oct 2022 Anton Bakhtin, David J Wu, Adam Lerer, Jonathan Gray, Athul Paul Jacob, Gabriele Farina, Alexander H Miller, Noam Brown

We then show that DiL-piKL can be extended into a self-play reinforcement learning algorithm we call RL-DiL-piKL that provides a model of human play while simultaneously training an agent that responds well to this human model.

reinforcement-learning Reinforcement Learning (RL)

Modeling Strong and Human-Like Gameplay with KL-Regularized Search

no code implementations14 Dec 2021 Athul Paul Jacob, David J. Wu, Gabriele Farina, Adam Lerer, Hengyuan Hu, Anton Bakhtin, Jacob Andreas, Noam Brown

We consider the task of building strong but human-like policies in multi-agent decision-making problems, given examples of human behavior.

Imitation Learning

No-Press Diplomacy from Scratch

1 code implementation NeurIPS 2021 Anton Bakhtin, David Wu, Adam Lerer, Noam Brown

Additionally, we extend our methods to full-scale no-press Diplomacy and for the first time train an agent from scratch with no human data.


Exploring generative atomic models in cryo-EM reconstruction

no code implementations3 Jul 2021 Ellen D. Zhong, Adam Lerer, Joseph H. Davis, Bonnie Berger

Although reconstruction algorithms typically model the 3D volume as a generic function parameterized as a voxel array or neural network, the underlying atomic structure of the protein of interest places well-defined physical constraints on the reconstructed structure.

Protein Folding

Learned Belief Search: Efficiently Improving Policies in Partially Observable Settings

no code implementations16 Jun 2021 Hengyuan Hu, Adam Lerer, Noam Brown, Jakob Foerster

Search is an important tool for computing effective policies in single- and multi-agent environments, and has been crucial for achieving superhuman performance in several benchmark fully and partially observable games.


Off-Belief Learning

5 code implementations6 Mar 2021 Hengyuan Hu, Adam Lerer, Brandon Cui, David Wu, Luis Pineda, Noam Brown, Jakob Foerster

Policies learned through self-play may adopt arbitrary conventions and implicitly rely on multi-step reasoning based on fragile assumptions about other agents' actions and thus fail when paired with humans or independently trained agents at test time.

CryoDRGN2: Ab Initio Neural Reconstruction of 3D Protein Structures From Real Cryo-EM Images

no code implementations ICCV 2021 Ellen D. Zhong, Adam Lerer, Joseph H. Davis, Bonnie Berger

In this work we describe cryoDRGN2, an ab initio reconstruction algorithm, which can jointly estimate image poses and learn a neural model of a distribution of 3D structures on real heterogeneous cryo-EM data.

Scalable Graph Neural Networks for Heterogeneous Graphs

1 code implementation19 Nov 2020 Lingfan Yu, Jiajun Shen, Jinyang Li, Adam Lerer

Graph neural networks (GNNs) are a popular class of parametric model for learning over graph-structured data.

Node Property Prediction

Ridge Rider: Finding Diverse Solutions by Following Eigenvectors of the Hessian

no code implementations NeurIPS 2020 Jack Parker-Holder, Luke Metz, Cinjon Resnick, Hengyuan Hu, Adam Lerer, Alistair Letcher, Alex Peysakhovich, Aldo Pacchiano, Jakob Foerster

In the era of ever decreasing loss functions, SGD and its various offspring have become the go-to optimization tool in machine learning and are a key component of the success of deep neural networks (DNNs).

BIG-bench Machine Learning

Human-Level Performance in No-Press Diplomacy via Equilibrium Search

no code implementations ICLR 2021 Jonathan Gray, Adam Lerer, Anton Bakhtin, Noam Brown

Prior AI breakthroughs in complex games have focused on either the purely adversarial or purely cooperative settings.

Combining Deep Reinforcement Learning and Search for Imperfect-Information Games

1 code implementation NeurIPS 2020 Noam Brown, Anton Bakhtin, Adam Lerer, Qucheng Gong

This paper presents ReBeL, a general framework for self-play reinforcement learning and search that provably converges to a Nash equilibrium in any two-player zero-sum game.

reinforcement-learning Reinforcement Learning (RL)

DREAM: Deep Regret minimization with Advantage baselines and Model-free learning

1 code implementation18 Jun 2020 Eric Steinberger, Adam Lerer, Noam Brown

We introduce DREAM, a deep reinforcement learning algorithm that finds optimal strategies in imperfect-information games with multiple agents.

reinforcement-learning Reinforcement Learning (RL)

"Other-Play" for Zero-Shot Coordination

2 code implementations6 Mar 2020 Hengyuan Hu, Adam Lerer, Alex Peysakhovich, Jakob Foerster

We consider the problem of zero-shot coordination - constructing AI agents that can coordinate with novel partners they have not seen before (e. g. humans).

Multi-agent Reinforcement Learning

Improving Policies via Search in Cooperative Partially Observable Games

10 code implementations5 Dec 2019 Adam Lerer, Hengyuan Hu, Jakob Foerster, Noam Brown

The first one, single-agent search, effectively converts the problem into a single agent setting by making all but one of the agents play according to the agreed-upon policy.

Game of Hanabi

Robust Multi-agent Counterfactual Prediction

no code implementations NeurIPS 2019 Alexander Peysakhovich, Christian Kroer, Adam Lerer

We consider the problem of using logged data to make predictions about what would happen if we changed the `rules of the game' in a multi-agent system.


PyTorch-BigGraph: A Large-scale Graph Embedding System

1 code implementation28 Mar 2019 Adam Lerer, Ledell Wu, Jiajun Shen, Timothee Lacroix, Luca Wehrstedt, Abhijit Bose, Alex Peysakhovich

Graph embedding methods produce unsupervised node features from graphs that can then be used for a variety of machine learning tasks.

 Ranked #1 on Link Prediction on YouTube (Macro F1 metric)

Graph Embedding graph partitioning +1

Deep Counterfactual Regret Minimization

4 code implementations1 Nov 2018 Noam Brown, Adam Lerer, Sam Gross, Tuomas Sandholm

This paper introduces Deep Counterfactual Regret Minimization, a form of CFR that obviates the need for abstraction by instead using deep neural networks to approximate the behavior of CFR in the full game.


Learning Existing Social Conventions via Observationally Augmented Self-Play

no code implementations26 Jun 2018 Adam Lerer, Alexander Peysakhovich

When there are multiple possible conventions we show that learning a policy via multi-agent reinforcement learning (MARL) is likely to find policies which achieve high payoffs at training time but fail to coordinate with the real group into which the agent enters.

Imitation Learning Multi-agent Reinforcement Learning +1

IntPhys: A Framework and Benchmark for Visual Intuitive Physics Reasoning

1 code implementation20 Mar 2018 Ronan Riochet, Mario Ynocente Castro, Mathieu Bernard, Adam Lerer, Rob Fergus, Véronique Izard, Emmanuel Dupoux

In order to reach human performance on complexvisual tasks, artificial systems need to incorporate a sig-nificant amount of understanding of the world in termsof macroscopic objects, movements, forces, etc.

Automatic Differentiation in PyTorch

1 code implementation NIPS 2017 2017 Adam Paszke, Sam Gross, Soumith Chintala, Gregory Chanan, Edward Yang, Zachary DeVito, Zeming Lin, Alban Desmaison, Luca Antiga, Adam Lerer

In this article, we describe an automatic differentiation module of PyTorch — a library designed to enable rapid research on machine learning models.

Clustering Dimensionality Reduction +1

Consequentialist conditional cooperation in social dilemmas with imperfect information

no code implementations ICLR 2018 Alexander Peysakhovich, Adam Lerer

We show how to construct such strategies using deep reinforcement learning techniques and demonstrate, both analytically and experimentally, that they are effective in social dilemmas beyond simple matrix games.

Prosocial learning agents solve generalized Stag Hunts better than selfish ones

no code implementations8 Sep 2017 Alexander Peysakhovich, Adam Lerer

We extend existing work on reward-shaping in multi-agent reinforcement learning and show that that making a single agent prosocial, that is, making them care about the rewards of their partners can increase the probability that groups converge to good outcomes.

Multi-agent Reinforcement Learning reinforcement-learning +1

A MultiPath Network for Object Detection

1 code implementation7 Apr 2016 Sergey Zagoruyko, Adam Lerer, Tsung-Yi Lin, Pedro O. Pinheiro, Sam Gross, Soumith Chintala, Piotr Dollár

To address these challenges, we test three modifications to the standard Fast R-CNN object detector: (1) skip connections that give the detector access to features at multiple network layers, (2) a foveal structure to exploit object context at multiple object resolutions, and (3) an integral loss function and corresponding network adjustment that improve localization.

Instance Segmentation Object +2

Learning Physical Intuition of Block Towers by Example

3 code implementations3 Mar 2016 Adam Lerer, Sam Gross, Rob Fergus

Wooden blocks are a common toy for infants, allowing them to develop motor skills and gain intuition about the physical behavior of the world.

Physical Intuition

Cannot find the paper you are looking for? You can Submit a new open access paper.