policy-learning

[IEEE T-PAMI 2024] All you need for End-to-end Autonomous Driving

A curated list of 3D Vision papers relating to Robotics domain in the era of large models i.e. LLMs/VLMs, inspired by awesome-computer-vision, including papers, codes, and related websites

[CVPR 2024 Highlight] GenAD: Generalized Predictive Model for Autonomous Driving

YLearn, a pun of "learn why", is a python package for causal inference

[ICLR 2023] Pytorch implementation of PPGeo, a fully self-supervised driving policy pre-training framework to learn from unlabeled driving videos.

[RSS 2024] Learning Manipulation by Predicting Interaction

[ECCV 2022] Learning to Drive by Watching YouTube Videos: Action-Conditioned Contrastive Policy Pretraining

Policy learning via doubly robust empirical welfare maximization over trees

Stable dynamical system (motion policy) learning using Euclideanizing flows

PyTorch code for TAPAS-GMM.

Off-Policy Evaluation and Learning that is both Doubly Robust and Distributionally Robust.

Experiment code for "Koopman Constrained Policy Optimization: a Koopman operator theoretic method for differentiable optimal control in robotics" as presented at ICML 2023

Black-box, gradient-free optimization of car-racing policies.

The official repository for Net Actor-Critic

[ECAI-2025] SPOWL: A JAX-based Safe RL framework that adaptively combines planning and policy learning with dynamic safety thresholds.

# Car_Black_Box This smart black box monitors key vehicle metrics in real-time, alerting drivers to unsafe conditions. With AI-driven insights, fleet managers can reduce accidents and maintenance costs effectively. 🚗💻

Neural network and reinforcement learning models for efficient decision-making on classical planning benchmarks

This repository 📂 implements Q-Learning 🤖 in Blackjack 🃏, comparing it with random action selection 🎲 and basic strategies 📋. Includes experiments 🔬 with various strategies, rule variations ⚖️, and deck numbers 🃏📦 to evaluate performance 📈.

Implementation of a basic diffusion policy in jax with a full pipeline of data collection -> data augmentation -> training -> inference/evaluation