Silvia's Projects
Implementation of "Active Exploration for Inverse Reinforcement Learning (AceIRL), NeurIPS 2022.
two-agents setting with minmax planner for counterfactual explanations - Learning from Explanations and Demonstrations: A Pilot Study
List of relevant resources for machine learning from explanatory supervision
Prototype of a game where a reinforcement learning agent is trained through natural language instructions
Bayesian Inverse Reinforcement Learning with simple environments
Brain-Computer Interface - data analysis, k nearest neighbors classifier
Codes to reproduce the results of the paper Contrastive Examples in Maximum Likelihood Inverse Reinforcement Learning
Code for Diagnosing Bottlenecks in Deep Q-learning. Contains implementations of tabular environments plus solvers.
multiplayer game and chat for collecting data on human counterfactual explanations in a collaborative learning task
The original repository for the game For the Record
Generalizing Persistent Advice in Interactive Reinforcement Learning Scenarios
Clean PyTorch implementations of imitation and reward learning algorithms
This is the website of the Computer Science Project course on Genetic Algorithms
minmax planner for suboptimal explanations with POMDP framework to optimize those explanations for the learner level of expertise
Inverse Reinforcement Learning from a Gradient-based Learner
Pytorch implementation of LOLA (https://arxiv.org/abs/1709.04326) using DiCE (https://arxiv.org/abs/1802.05098)
collections of vanilla ML models implemented with existing python libraries and simple datasets
Collection of Python classes
This repository basically covers Python implementation of different machine learning algorithms like Linear Regression, Logistic regression, Decision tree, PCA,SVM, kNN. It also has implementation of NLP and Recommender System.
It is Python script able to impose a single page pdf into ready-to-print booklet.
This repositoy contains a Jupyter Notebook with an implemenation of a Q-Learning Agent, which learns to solve the n-Chain OpenAI Gym environment
A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.
Sequential Explanations with Mental Model-Based Policies (Reinforcement Learning for Explainable AI)
multi-armed bandit, gambler problem, cliff problem and TD learning
a Lightweight library for sequential learning agents, including reinforcement learning
gym compatible customized gridworld environments
Config files for my GitHub profile.
Introductory tutorial to build a Flask web application that integrates a machine learning model. The dummy example takes the mood and the hours of sleep of the user as a numerical input and predicts the workload in hours.
software tool for solving a single machine scheduling (SMS) problem using a MiniZinc framework for constraint satisfaction problems (CSP)