Search Results for author:
Found 32 papers, 17 papers with code
“Other-Play” for Zero-Shot Coordination
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
Current language models often fail to incorporate long contexts efficiently during generation.
Human-level play in the game of Diplomacy by combining language models with strategic reasoning
Despite much progress in training AI systems to imitate human language, building agents that use language to communicate intentionally with humans in interactive environments remains a major challenge.
Human-AI Coordination via Human-Regularized Search and Learning
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
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.
Efficient Heterogeneous Treatment Effect Estimation With Multiple Experiments and Multiple Outcomes
Learning heterogeneous treatment effects (HTEs) is an important problem across many fields.
Modeling Strong and Human-Like Gameplay with KL-Regularized Search
We consider the task of building strong but human-like policies in multi-agent decision-making problems, given examples of human behavior.
No-Press Diplomacy from Scratch
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
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.
Learned Belief Search: Efficiently Improving Policies in Partially Observable Settings
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
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
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
Graph neural networks (GNNs) are a popular class of parametric model for learning over graph-structured data.
Ranked #20 on
Node Property Prediction
on ogbn-mag
Ridge Rider: Finding Diverse Solutions by Following Eigenvectors of the Hessian
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).
Human-Level Performance in No-Press Diplomacy via Equilibrium Search
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
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.
DREAM: Deep Regret minimization with Advantage baselines and Model-free learning
We introduce DREAM, a deep reinforcement learning algorithm that finds optimal strategies in imperfect-information games with multiple agents.
"Other-Play" for Zero-Shot Coordination
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).
Improving Policies via Search in Cooperative Partially Observable Games
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.
PyTorch: An Imperative Style, High-Performance Deep Learning Library
Deep learning frameworks have often focused on either usability or speed, but not both.
Robust Multi-agent Counterfactual Prediction
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
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)
Deep Counterfactual Regret Minimization
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
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.
IntPhys: A Framework and Benchmark for Visual Intuitive Physics Reasoning
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.
Composable Planning with Attributes
The tasks that an agent will need to solve often are not known during training.
Automatic Differentiation in PyTorch
In this article, we describe an automatic differentiation module of PyTorch — a library designed to enable rapid research on machine learning models.
Consequentialist conditional cooperation in social dilemmas with imperfect information
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
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
Maintaining cooperation in complex social dilemmas using deep reinforcement learning
Social dilemmas are situations where individuals face a temptation to increase their payoffs at a cost to total welfare.
A MultiPath Network for Object Detection
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.
Ranked #104 on
Instance Segmentation
on COCO test-dev
Learning Physical Intuition of Block Towers by Example
Wooden blocks are a common toy for infants, allowing them to develop motor skills and gain intuition about the physical behavior of the world.
