Jessica Hamrick
Jessica Hamrick
Latest posts
Planning, reasoning, and generalisation in deep learning
Talk presented at the Royal Society meeting titled “Beyond the symbols vs signals debate”.
Blog
Presentations
Publications
Intuitive physics as probabilistic inference
Transformers meet Neural Algorithmic Reasoners
Beyond Temporal Credit Assignment in Reinforcement Learning
Understanding and improving model-based deep RL
Talk presented in the Imperial College London ICARL Seminar Series
Investigating the role of model-based learning in exploration and transfer
On the role of planning in model-based deep RL
Talk presented at the CCN GAC titled “What is the place of planning?”.
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
Tutorial on model-based reinforcement learning
Tutorial presented at ICML 2020 with Igor Mordatch.
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
Structured agents for physical construction
Talk presented at ICML 2019.
Structured computation and representation in deep RL
Presented at the Workshop on Structured Prediction meets Deep Reinforcement Learning, ICLR 2019
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
nbgrader: A Tool for Creating and Grading Assignments in the Jupyter Notebook
Presented at SciPy 2017
Discovering simple heuristics from mental simulation
Metacontrol for Adaptive Imagination-Based Optimization
Metareasoning and Mental Simulation
Pragmatic-Pedagogic Value Alignment
Reproducible, One Button Workflows with the Jupyter Notebook & Scons
Presented at SciPy 2016
Creating Reproducible, Publication-Quality Plots with Matplotlib and Seaborn
Update: this post was created from a Jupyter notebook, which you can access here . How should you create a plot for inclusion in a publication? A common workflow for Matlab or Python users—and one that I used to use myself—is to create a figure just using the defaults, export it as SVG, and open it Inkscape or Illustrator to make it look nice. This works fine if you only need to edit how a figure…
Passing Quals!
A few weeks ago, on January 25th 2016, I passed my qualifying exams! This means that I am now qualified to write my thesis and get my PhD. Passing quals involved a lot of reading; during January I was reading pretty much 5 papers per day: Different people prepare for quals in different ways. One of my labmates prepared by writing hand-written notes in many small notebooks and then scanning them.…
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
Teaching with IPython: Jupyter Notebooks and JupyterHub
Presented at SciPy 2015
Deploying JupyterHub for Education
Over the last few months, I’ve been busily working on converting a class that I am a TA for from Matlab to Python. Actually, not just Python, but IPython/Jupyter notebooks! Part of this involved setting up a server that the students could log in to in order to complete their assignments. I wrote a post over on the Rackspace developer blog about it:…
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
How I learned to stop worrying and love PyCon
Ok, I’ll admit it. I was pretty nervous about going to PyCon. I was giving a talk , I was only going to know a couple of people there, I was going for an entire week, and it was going to be in a city where they speak a language of which I only know about two words. Also, I was a bit unsure of what to expect in terms of the social climate (especially given that the only other non-academic…
Python Koans with the IPython Notebook
Short version: As a proof of concept, I converted the Python koan about_strings (which you can find here , for Python 2, or here , for Python 3) into an IPython notebook. Here’s the notebook on nbviewer . Long version: Every week, a group of Python enthusiasts around Berkeley get together to talk about various Python things. This past week, we talked about Greg Malcom’s wonderful…