An implementation of Monte Carlo Tree Search in python

General Python implementation of Monte Carlo Tree Search for the use with Open AI Gym environments.

Official implementation for "Towards Safe Reinforcement Learning via Constraining Conditional Value at Risk" (IJCAI 2022)

Official PyTorch implementation of Lumos: Learning Visual Generative Priors without Text

Implementation of centralized training, centralized execution of Soft Actor-Critic (SAC) on a Tennis multiagent Unity environment.

This is the source code for Detecting Machine-Generated Texts by Multi-Population Aware Optimization for Maximum Mean Discrepancy (ICLR2024).

Maximum Entropy Population Based Training for Zero-Shot Human-AI Coordination

Implement some reinforcement learning algorithms, test and visualize on Pacman.

Fundamental of AI course which focuses on search, multiagents, mdp and reinforcement learning algorithms.

This project focuses on agent-based modelling, non-cooperative and cooperative games, and sequential decision-making under uncertainty.

Level-based Foraging (LBF): A multi-agent environment for RL

Codebase for BRDiv: Diverse teammate generation for ad hoc teamwork

Implementation of VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning - Zintgraf et al. (ICLR 2020)

Simple reinforcement learning framework for selfplay experiments

PyTorch implementation of two variational autoencoders -- one with the classical KL divergence metric and one using the MMD.

Code for the paper HyperDynamics: Meta-Learning Object and Agent Dynamics with Hypernetworks (ICLR 2021).

Code for "Actor-Attention-Critic for Multi-Agent Reinforcement Learning" ICML 2019

Code for a multi-agent particle environment used in the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"

PyTorch implementation of DQN, AC, ACER, A2C, A3C, PG, DDPG, TRPO, PPO, SAC, TD3 and ....

An Implementation of PPO for environments with multiple agents

Minimal implementation of clipped objective Proximal Policy Optimization (PPO) in PyTorch

Implementation of vanilla stochaistic (categorical) policy gradient algorithm to play cartpole.

Implementing different learning algorithms and analyzing their performance in a Markov game model called the Soccer Game

Soccer toy example simulator used in Reinforcement Learning

Demonstration of Diversity Inducing Policy Gradient (DIPG)

Code to train RL agents along with Adversarial distrubance agents

Implementation of Robust Adversarial Reinforcement Learning

Experimenting with meta-learning approaches to opponent modelling in MARL. Building upon previous public implementations of MADDPG and M3DDPG.

Implementation of Conditional Generative Adversarial Networks in PyTorch