Planning with Diffusion for Flexible Behavior Synthesis
Offered By: Generative Memory Lab via YouTube
Course Description
Overview
Explore cutting-edge research on flexible behavior synthesis in this 40-minute presentation by MIT EECS PhD student Yilun Du. Delve into the innovative approach of planning with diffusion for generating adaptive trajectories and behaviors. Learn about neural networks combined with trajectory optimization, generative modeling for planning, and compositional trajectory generation. Discover the Diffuser model's capabilities in variable-length predictions and flexible behavior synthesis through distribution composition. Examine advanced techniques such as goal planning through inpainting, test-time cost specification, and offline reinforcement learning with value guidance. Gain insights into the application of test-time cost functions and their impact on behavior synthesis.
Syllabus
Intro
Neural nets + trajectory optimization
Is the model the bottleneck?
Planning as generative modeling
A generative model of trajectories
Compositional trajectory generation
Sampling from Diffuser
Variable-length predictions
Flexible Behavior Synthesis through Composing Distributions
Goal Planning through Inpainting
Test-Time Cost Specification
Offline Reinforcement Learning through Value Guidance
Test-Time Cost Functions
Taught by
Generative Memory Lab
Related Courses
Deep Learning – Part 2Indian Institute of Technology Madras via Swayam Probabilistic Deep Learning with TensorFlow 2
Imperial College London via Coursera Introduction to Deep Learning
Massachusetts Institute of Technology via YouTube Spatial Computational Thinking
National University of Singapore via edX DALL-E - Zero-Shot Text-to-Image Generation - Paper Explained
Aleksa Gordić - The AI Epiphany via YouTube