mike-gimelfarb
Researcher in artificial intelligence and reinforcement learning.
University of TorontoToronto
Pinned Repositories
bayesian-epsilon-greedy
Public repository for a paper in UAI 2019 describing adaptive epsilon-greedy exploration using Bayesian ensembles for deep reinforcement learning.
bayesian-reward-shaping
Bayesian Reward Shaping Framework for Deep Reinforcement Learning
bboptpy
Powerful and scalable black-box optimization algorithms for Python and C++.
cascade-correlation-neural-networks
A general framework for cascade correlation architectures in Python with wrappers to keras, tensorflow and sklearn
contextual-policy-reuse-deep-rl
Framework for Contextually Transferring Knowledge from Multiple Source Policies in Deep Reinforcement Learning
deep-successor-features-for-transfer
A reusable framework for successor features for transfer in deep reinforcement learning using keras.
numerical-integration
a curated collection of algorithms for performing numerical integration of black-box functions and estimating limits of series and sequences with high precision in Java
optim4j
Library for numerical optimization of functions written in pure Java.
pyRDDLGym
A toolkit for auto-generation of OpenAI Gym environments from RDDL description files.
pyRDDLGym-jax
JAX compilation of RDDL description files, and a differentiable planner in JAX.
mike-gimelfarb's Repositories
mike-gimelfarb/deep-successor-features-for-transfer
A reusable framework for successor features for transfer in deep reinforcement learning using keras.
mike-gimelfarb/bayesian-reward-shaping
Bayesian Reward Shaping Framework for Deep Reinforcement Learning
mike-gimelfarb/cascade-correlation-neural-networks
A general framework for cascade correlation architectures in Python with wrappers to keras, tensorflow and sklearn
mike-gimelfarb/bayesian-epsilon-greedy
Public repository for a paper in UAI 2019 describing adaptive epsilon-greedy exploration using Bayesian ensembles for deep reinforcement learning.
mike-gimelfarb/bboptpy
Powerful and scalable black-box optimization algorithms for Python and C++.
mike-gimelfarb/numerical-integration
a curated collection of algorithms for performing numerical integration of black-box functions and estimating limits of series and sequences with high precision in Java
mike-gimelfarb/contextual-policy-reuse-deep-rl
Framework for Contextually Transferring Knowledge from Multiple Source Policies in Deep Reinforcement Learning
mike-gimelfarb/optim4j
Library for numerical optimization of functions written in pure Java.
mike-gimelfarb/mfpy
A very simple framework for solving MDPs using model-free reinforcement learning.
mike-gimelfarb/bayesian-experience-reuse
Appendix for the IJCAI 2021 submission entitled "Bayesian Experience Reuse for Learning from Multiple Demonstrators"
mike-gimelfarb/gamma-models
Code for the paper "Gamma-Models: Generative Temporal Difference Learning for Infinite-Horizon Prediction"
mike-gimelfarb/JaxPlan-GurobiPlan-ICAPS-2024
Experiments for ICAPS 2024 paper " JaxPlan and GurobiPlan: Optimization Baselines for Replanning in Discrete and Mixed Discrete-Continuous Probabilistic Domains"
mike-gimelfarb/LineSearches.jl
Line search methods for optimization and root-finding
mike-gimelfarb/mike-gimelfarb
mike-gimelfarb/mike-gimelfarb.github.io
Personal website based on jekyll theme.
mike-gimelfarb/Recession-Predictor
Project description: https://medium.com/p/recession-prediction-using-machine-learning-de6eee16ca94?source=email-2adc3d3cd2ed--writer.postDistributed&sk=2f1dab9738769f9658634e61576a08bd