johan-kallstrom's Projects
Mean Field Multi-Agent Reinforcement Learning
Simple and easily configurable 3D FPS-game-like environments for reinforcement learning
Multi-objective Gymnasium environments for reinforcement learning
Multi-Objective Reinforcement Learning
Multi-Objective Reinforcement Learning algorithms implementations.
Sccheduling Environment for Multi-Robot Coordination Problems
Environment generation code for the paper "Emergent Tool Use From Multi-Agent Autocurricula"
Using RLLib and PycoLab to explore intelligent cooperative behavior in sequential social dilemmas
Code for the paper "Emergent Complexity via Multi-agent Competition"
Code for a multi-agent particle environment used in the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"
Benchmark for Continuous Multi-Agent Robotic Control, based on OpenAI's Mujoco Gym environments.
This is the official implementation of Multi-Agent PPO (MAPPO).
A Tensorflow implementation of the Option-Critic Architecture
Implementation of Option Critic with Deliberation Cost in Tensorflow
Implementation of the Option-Critic Architecture
Implementation of the Option-Critic Architecture on the Atari (ALE) environment
Gym for multi-agent reinforcement learning
[ICML 2020] Prediction-Guided Multi-Objective Reinforcement Learning for Continuous Robot Control
Proximal Policy Option-Critic
Implementation of the Prioritized Option-Critic on the Four-Rooms Environment
Python implementation of behaviour trees.
Fine-tuned MARL algorithms in SMAC (100% win rates on most scenarios)
QMIX implemented in TensorFlow 2
Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.
Retro Games in Gym
Structural implementation of RL key algorithms
High-Power Rocketry 6 DOF Trajectory Simulation
Safe Option-Critic: Learning Safety in the Option-Critic Architecture