Pinned Repositories
certified-regretnet
dynamic_matching
ice
Python code that implements the Inverse Correlated Equilibrium optimization
kidney_solver
Solve kidney-exchange instances using Python 2 and Gurobi
mandelbrot-clj
A simple mandelbrot fractal viewer using Quil/Processing
o2lsh
An implementation of locality sensitive hashing in Rust
PolyaGammaDistribution.jl
Pólya-Gamma distribution for Distributions.jl interface
SinkhornDistance.jl
structure2vec-tf
(start of) implementing structure2vec in just tensorflow. please do not use this repository, it isn't even close to working.
two-player-auctions
JAX/Haiku implementation of "Auction Learning as a Two-Player Game"
currymj's Repositories
currymj/SinkhornDistance.jl
currymj/PolyaGammaDistribution.jl
Pólya-Gamma distribution for Distributions.jl interface
currymj/certified-regretnet
currymj/ice
Python code that implements the Inverse Correlated Equilibrium optimization
currymj/two-player-auctions
JAX/Haiku implementation of "Auction Learning as a Two-Player Game"
currymj/dynamic_matching
currymj/kidney_solver
Solve kidney-exchange instances using Python 2 and Gurobi
currymj/ridesharing-gym
currymj/aaai_melding_code
Code the AAAI 2019 paper "Melding the Data-Decisions Pipeline: Decision-Focused Learning for Combinatorial Optimization"
currymj/aoc2018
advent of code 2018
currymj/currymj.github.io
currymj/deepqmc
Deep learning quantum Monte Carlo for electrons in real space
currymj/DiffOpt.jl
Differentiating convex optimization programs w.r.t. program parameters
currymj/distrax
currymj/dynamic-set-packing-gym
currymj/dynsetpack-jl
currymj/estimators
Estimators to perform off-policy evaluation
currymj/iclr-blog-track.github.io
currymj/jaxamples
some sketches as i try to kick the tires with jax
currymj/open_spiel
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
currymj/pysats
currymj/pytorch-a2c-ppo-acktr-gail
PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).
currymj/pytorch_correq
currymj/qanta-codalab
QANTA Competition: Baseline System
currymj/sats
Library to generate Spectrum Auction Test Instances in Java
currymj/secure-ml-workshop.github.io
currymj/simple_no_regret
currymj/sinkhorn_predict_optimizer
currymj/smt_class_schedules
solving constrained schedules with Z3 as a learning exercise
currymj/torch_test
test of torch c++ interface