• Publications
  • Influence
Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning
The ability to act in multiple environments and transfer previous knowledge to new situations can be considered a critical aspect of any intelligent agent. Towards this goal, we define a novel methodExpand
  • 293
  • 33
Neuro-Symbolic Program Synthesis
Recent years have seen the proposal of a number of neural architectures for the problem of Program Induction. Given a set of input-output examples, these architectures are able to learn mappings thatExpand
  • 150
  • 17
Generating Images from Captions with Attention
Motivated by the recent progress in generative models, we introduce a model that generates images from natural language descriptions. The proposed model iteratively draws patches on a canvas, whileExpand
  • 206
  • 10
Neural Map: Structured Memory for Deep Reinforcement Learning
A critical component to enabling intelligent reasoning in partially observable environments is memory. Despite this importance, Deep Reinforcement Learning (DRL) agents have so far used relativelyExpand
  • 128
  • 5
The Hanabi Challenge: A New Frontier for AI Research
Abstract From the early days of computing, games have been important testbeds for studying how well machines can do sophisticated decision making. In recent years, machine learning has made dramaticExpand
  • 45
  • 5
Global Pose Estimation with an Attention-Based Recurrent Network
The ability for an agent to localize itself within an environment is crucial for many real-world applications. For unknown environments, Simultaneous Localization and Mapping (SLAM) enablesExpand
  • 31
  • 4
Gated Path Planning Networks
Value Iteration Networks (VINs) are effective differentiable path planning modules that can be used by agents to perform navigation while still maintaining end-to-end differentiability of the entireExpand
  • 27
  • 4
Active Neural Localization
Localization is the problem of estimating the location of an autonomous agent from an observation and a map of the environment. Traditional methods of localization, which filter the belief based onExpand
  • 38
  • 3
Efficient Exploration via State Marginal Matching
Exploration is critical to a reinforcement learning agent's performance in its given environment. Prior exploration methods are often based on using heuristic auxiliary predictions to guide policyExpand
  • 21
  • 2
Stabilizing Transformers for Reinforcement Learning
Owing to their ability to both effectively integrate information over long time horizons and scale to massive amounts of data, self-attention architectures have recently shown breakthrough success inExpand
  • 13
  • 1