Continual Reinforcement Learning in 3D Non-stationary Environments

This is a pip package implementing Reinforcement Learning algorithms in non-stationary environments supported by the OpenAI Gym toolkit.

Code associated with the NeurIPS19 paper "Weighted Linear Bandits in Non-Stationary Environments"

Experiments for paper "Online Learning with Costly Features in Non-stationary Environments"

Queue-Based Resampling (QBR, ICANN 2018)

Code for the manuscript 'Hierarchy of prediction errors shapes the learning of context-dependent sensory representations'

R package to apply the transformed-stationary extreme value analysis

The implementation of the Diversity Pool algorithm, proposed in the paper "Diversity-Based Pool of Models for Dealing with Recurring Concepts" and presented at IJCNN '18

Repo for course CSC2558: "Intelligent Adaptive Interventions" project in nonstationary contextual bandits.

Matlab laboratories for the course "Online Learning and Monitoring" at Politecnico di Milano

Mitigating the Stability-Plasticity Dilemma in Adaptive Train Scheduling with Curriculum-Driven Continual DQN Expansion

Work for CDC2020