fratim

SelectToPerfect

Code for the 2024 ICLR paper "Select to Perfect: Imitating desired behavior from large multi-agent data"

Illu-Attacks-Jax

Code for the ICLR 2024 Paper "Illusory Attacks: Information-theoretic detectability matters in adversarial attacks"

UDIL

acme

A library of reinforcement learning components and agents

auto-attack

Code relative to "Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks"

diffusion-relative-rewards

Code for the 2023 NeurIPS paper "Extracting Reward Functions from Diffusion Models"

gym-minigrid

Minimalistic gridworld package for OpenAI Gym

HelloFresh

Code for the 2024 ACL paper "HelloFresh: LLM Evaluations on Streams of Real-World Human Editorial Actions across X Community Notes and Wikipedia edits".

rl-starter-files

RL starter files in order to immediatly train, visualize and evaluate an agent without writing any line of code

torch-ac

Recurrent and multi-process PyTorch implementation of deep reinforcement Actor-Critic algorithms A2C and PPO

B16Examples

gym-multigrid

Lightweight multi-agent gridworld Gym environment

imitation

Clean PyTorch implementations of imitation and reward learning algorithms

Inverse-Reinforcement-Learning

Implementations of selected inverse reinforcement learning algorithms.

irl-maxent

Maximum Entropy and Maximum Causal Entropy Inverse Reinforcement Learning Implementation in Python

lbf

A multi-agent environment for RL

MADDPG

Pytorch implementation of the MARL algorithm, MADDPG, which correspondings to the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments".

minerl

MineRL Competition for Sample Efficient Reinforcement Learning - Python Package

minerl2020_submission

minerl_singularity

nips_figures

PettingZoo

Gym for multi-agent reinforcement learning

pfrl

PFRL: a PyTorch-based deep reinforcement learning library

Pyro4

Pyro 4.x - Python remote objects

seals

Benchmark environments for reward modelling and imitation learning algorithms.

stable-baselines3

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

udil-code

vfunctions

Value Functions

website_simple

A beautiful, simple, clean, and responsive Jekyll theme for academics

yaspi

yaspi - Yet Another Slurm Python Interface