RLinf is a distributed reinforcement learning orchestrator and embodied AI training framework. It provides the infrastructure to train vision-language-action models and robotic policies using a combination of reinforcement learning and supervised fine-tuning. The system is designed for scaling workloads across GPU clusters, managing the placement of actors, rollout workers, and environment components. It features a specialized robotics data collection pipeline for gathering teleoperated demonstrations and simulation trajectories into standardized replay buffers, alongside a hardware interface
PrefPaint: Aligning Image Inpainting Diffusion Model with Human Preference
The codebase is still being updated. We will soon add detailed instructions.
The main features of wrk8/dmbp are: Offline Reinforcement Learning.
Open-source alternatives to wrk8/dmbp include: rlinf/rlinf — RLinf is a distributed reinforcement learning orchestrator and embodied AI training framework. It provides the… guangheli12/diffstitch — cd scripts/mopo python train.py. kenkenzaii/prefpaint — PrefPaint: Aligning Image Inpainting Diffusion Model with Human Preference. ldcq/ldcq. liuxhym/edis — This repo contains the code of Energy-guided DIffusion Sampling (EDIS) algorithm, proposed by Energy-Guided Diffusion… ewanlee/hdmi — The codebase is still being updated. We will soon add detailed instructions.