Jessica Hamrick
  • About Me
  • Publications
  • Presentations
  • Blog
  • Talks
    • Planning, reasoning, and generalisation in deep learning
    • Understanding and improving model-based deep RL
    • On the role of planning in model-based deep RL
    • Tutorial on model-based reinforcement learning
    • Structured agents for physical construction
    • Structured computation and representation in deep RL
    • nbgrader: A Tool for Creating and Grading Assignments in the Jupyter Notebook
    • Reproducible, One Button Workflows with the Jupyter Notebook & Scons
    • Teaching with IPython: Jupyter Notebooks and JupyterHub
  • Blog
  • Presentations
  • Publications
  • Publications
    • Intuitive physics as probabilistic inference
    • Transformers meet Neural Algorithmic Reasoners
    • Beyond Temporal Credit Assignment in Reinforcement Learning
    • Investigating the role of model-based learning in exploration and transfer
    • Inverse design for fluid-structure interactions using graph network simulators
    • Learning causal overhypotheses through exploration in children and computational models
    • Procedural generalization by planning with self-supervised world models
    • On the role of planning in model-based deep reinforcement learning
    • Combining Q-Learning and Search with Amortized Value Estimates
    • Divide-and-Conquer Monte Carlo Tree Search For Goal-Directed Planning
    • Exploring Exploration: Comparing Children with RL Agents in Unified Environments
    • Levels of Analysis for Machine Learning
    • Analogues of mental simulation and imagination in deep learning
    • nbgrader: A Tool for Creating and Grading Assignments in the Jupyter Notebook
    • Object-oriented state editing for HRL
    • Structured agents for physical construction
    • Relational inductive bias for physical construction in humans and machines
    • Relational inductive biases, deep learning, and graph networks
    • Discovering simple heuristics from mental simulation
    • Metacontrol for Adaptive Imagination-Based Optimization
    • Metareasoning and Mental Simulation
    • Pragmatic-Pedagogic Value Alignment
    • A Rejection Sampler
    • Generating plans that predict themselves
    • Goal Inference Improves Objective and Perceived Performance in Human-Robot Collaboration
    • Imagination-Based Decision Making with Physical Models in Deep Neural Networks
    • Inferring Mass in Complex Scenes by Mental Simulation
    • Jupyter Notebooks—A publishing format for reproducible computational workflows
    • psiTurk: An open-source framework for conducting replicable behavioral experiments online
    • Relevant and Robust: A Response to Marcus and Davis (2013)
    • Think again? The amount of mental simulation tracks uncertainty in the outcome
    • Algorithm selection by rational metareasoning as a model of human strategy selection
    • What to simulate? Inferring the right direction for mental rotation
    • Approximating Bayesian inference with a sparse distributed memory system
    • Mental Rotation as Bayesian Quadrature
    • Simulation as an engine of physical scene understanding
    • Physical Reasoning in Complex Scenes is Sensitive to Mass
    • Internal physics models guide probabilistic judgments about object dynamics
  • Blog
    • Creating Reproducible, Publication-Quality Plots with Matplotlib and Seaborn
    • Passing Quals!
    • Deploying JupyterHub for Education
    • How I learned to stop worrying and love PyCon
    • Python Koans with the IPython Notebook
    • Installing 64-bit Panda3D for Python 2.7 on OS X
    • Rewriting Python docstrings with a metaclass
    • On collecting data
    • Switching to Octopress
    • Why is making a git commit so complicated?
    • Macs and Emacs
    • Emacs as a Python IDE
    • Absolute Beginner's Guide to Emacs
    • Saving figures from pyplot
    • The Demise of For Loops
    • An Introduction to Classes and Inheritance (In Python)
    • In Search of the Perfect Email Solution
    • Asking Good Questions (To Receive Great Answers)
    • A Brief Update, and Why Numpy is Awesome
    • Social Problems in Computer Science
    • Karl Taylor Compton Prize
    • SIPB's CPW
    • Hackasaurus Rex
    • Rustic Change Purse

Combining Q-Learning and Search with Amortized Value Estimates

Jan 1, 2020·
J. B. Hamrick
,
V. Bapst
,
A. Sanchez-Gonzalez
,
T. Pfaff
,
T. Weber
,
L. Buesing
,
P. W. Battaglia
· 0 min read
PDF Cite Video REVIEWS
Type
2
Publication
Proceedings of the International Conference on Learning Representations (ICLR 2020)
Last updated on Jan 1, 2020
← On the role of planning in model-based deep reinforcement learning Jan 1, 2021
Divide-and-Conquer Monte Carlo Tree Search For Goal-Directed Planning Jan 1, 2020 →

© 2025 Me. This work is licensed under CC BY NC ND 4.0

Published with Hugo Blox Builder — the free, open source website builder that empowers creators.