Pinned Repositories
InverseHyperplanes.jl
Multi-agent collision-avoidance using hyperplanes learned from expert trajectories by solving an inverse game.
ALPaCA
JAX implementation of "Meta-Learning Priors for Efficient Online Bayesian Regression" by Harrison et al.
aoc
My solutions for Advent of Code
discrete-rl
Q-Learning for Frozen Lake Environment
dvbf
gp
Gaussian process implementation
hello_ConformalPrediction.jl
hello_gpt
hello_MNIST
Simple MNIST classifier
InverseHyperplanes.jl
Collision-free trajectories for non-cooperative multi-agent systems using rotating hyperplane inferred from expert data.
fernandopalafox's Repositories
fernandopalafox/ALPaCA
JAX implementation of "Meta-Learning Priors for Efficient Online Bayesian Regression" by Harrison et al.
fernandopalafox/aoc
My solutions for Advent of Code
fernandopalafox/discrete-rl
Q-Learning for Frozen Lake Environment
fernandopalafox/dvbf
fernandopalafox/gp
Gaussian process implementation
fernandopalafox/hello_ConformalPrediction.jl
fernandopalafox/hello_gpt
fernandopalafox/hello_MNIST
Simple MNIST classifier
fernandopalafox/InverseHyperplanes.jl
Collision-free trajectories for non-cooperative multi-agent systems using rotating hyperplane inferred from expert data.
fernandopalafox/jaxgpt
Tiny Shakespeare GPT with JAX
fernandopalafox/ParametricMCPs.jl
Mixed complementarity problems parameterized by a "runtime"-parameter vector with support for implicit differentiation.
fernandopalafox/sqp-solver.jl
Find solutions to nonlinearly constrained optimization problems by solving quadratic subproblems.