OpenDILab Decision AI Engine. The Most Comprehensive Reinforcement Learning Framework B.P.

Clean PyTorch implementations of imitation and reward learning algorithms

Implementations of selected inverse reinforcement learning algorithms.

Inverse RL algorithms (APP, MaxEnt, GAIL, VAIL)

Implementation of Inverse Reinforcement Learning (IRL) algorithms in Python/Tensorflow. Deep MaxEnt, MaxEnt, LPIRL

TensorFlow2 Reinforcement Learning

Personal notes about scientific and research works on "Decision-Making for Autonomous Driving"

Master classic RL, deep RL, distributional RL, inverse RL, and more using OpenAI Gym and TensorFlow with extensive Math

(NeurIPS '21 Spotlight) IQ-Learn: Inverse Q-Learning for Imitation

DI-engine docs (Chinese and English)

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

[T-ITS] Driving Behavior Modeling using Naturalistic Human Driving Data with Inverse Reinforcement Learning

A selection of state-of-the-art research materials on decision making and motion planning.

Tensorflow implementation of generative adversarial imitation learning

Tutorial4RL: Tutorial for Reinforcement Learning. 强化学习入门教程.

A unified end-to-end learning and control framework that is able to learn a (neural) control objective function, dynamics equation, control policy, or/and optimal trajectory in a control system.

Implementation of Inverse Reinforcement Learning Algorithm on a toy car in a 2D world problem, (Apprenticeship Learning via Inverse Reinforcement Learning Abbeel & Ng, 2004)

Code for the ACL paper "No Metrics Are Perfect: Adversarial Reward Learning for Visual Storytelling"

Predicting Goal-directed Human Attention Using Inverse Reinforcement Learning (CVPR2020)

Tensorflow implementation of Generative Adversarial Imitation Learning(GAIL) with discrete action

Adversarial Imitation Via Variational Inverse Reinforcement Learning

DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents

official implementation of ICLR'2025 paper: Rethinking Bradley-Terry Models in Preference-based Reward Modeling: Foundations, Theory, and Alternatives

Pytorch GAIL VAIL AIRL VAIRL EAIRL SQIL Implementation

[RSS 2025] CREStE: Scalable Mapless Navigation with Internet Scale Priors and Counterfactual Guidance

A curated list of awesome multi-agent learning papers

SAILOR is an inverse RL algorithm that learns world and reward models to search at test-time and recover from mistakes.

Inverse Reinforcement Learning Argorithms

Contains implementation of the FILTER algorithm for exponentially faster inverse reinforcement learning.

Deep Reinforcement Learning algorithms implemented in PyTorch