Multi-Objective Reinforcement Learning algorithms implementations.

Multi-objective Gymnasium environments for reinforcement learning

AutoOED: Automated Optimal Experimental Design Platform

[ICML 2020] Prediction-Guided Multi-Objective Reinforcement Learning for Continuous Robot Control

[NeurIPS 2020] Diversity-Guided Efficient Multi-Objective Optimization With Batch Evaluations

A dependency free library of standardized optimization test functions written in pure Python.

Genetic Algorithm (GA) for a Multi-objective Optimization Problem (MOP)

MOEA/D is a general-purpose algorithm framework. It decomposes a multi-objective optimization problem into a number of single-objective optimization sub-problems and then uses a search heuristic to optimize these sub-problems simultaneously and cooperatively.

DeepCoord: Self-Learning Network and Service Coordination Using Deep Reinforcement Learning

Surrogate-Based Architecture Optimization toolbox

Extended, multi-agent, and multi-objective (MaMoRL / MoMaRL) gridworld environments building framework based on DeepMind's AI Safety Gridworlds. This is a suite of reinforcement learning environments illustrating various safety properties of intelligent agents. It is made compatible with OpenAI's Gym/Gymnasium and Farama Foundation PettingZoo.

Bayesian Optimization and Uncertainty Analyses Tools

Paxplot is a Python visualization library for parallel axis, or parallel coordinate, plots.

Python Multi-Objective Simulation Optimization: a package for using, implementing, and testing simulation optimization algorithms.

Code for the paper Optimistic Linear Support and Successor Features as a Basis for Optimal Policy Transfer - ICML 2022

An algorithm to calculate all pure strategy Nash equilibria in multi-objective games with quasiconvex utility functions

Multi-Objective Multi-Armed Bandit

Safety challenges for AI agents' ability to learn and act in desired ways in relation to biologically and economically relevant aspects. The benchmarks are implemented in a gridworld-based environment. The environments are relatively simple, just as much complexity is added as is necessary to illustrate the relevant safety and performance aspects.

Explanation system for semi-supervised multi-objective optimization