This course aims to teach learners about advancing embodied AI for machine autonomy. The learning outcomes include understanding sequential decision making in complex environments, utilizing data from existing simulation environments, generating new environments procedurally, benchmarking RL generalization, safe reinforcement learning, and multi-agent reinforcement learning. The course covers skills such as pretraining policy representation with real-world data, self-supervised learning through contrastive learning, and policy pretraining with human actions. The teaching method includes lectures, demonstrations, and real-world examples. The intended audience for this course is individuals interested in artificial intelligence, machine learning, and autonomous systems.
Overview
Syllabus
Intro
Sequential Decision Making in Complex Environments
Data from the Existing Simulation Environments
Procedural Generation of New Environments
Benchmarking RL Generalization
Benchmarking Safe Reinforcement Learning
Benchmarking Multi-Agent Reinforcement Learning
Real2Sim: Learning to generate traffic scenarios
Pretraining Policy Representation with Real World Data
Self-supervised Learning through Contrastive Learning
Policy Pretraining with Human Actions
Action-conditioned Contrastive Learning
Pretrained Representation for Imitation Learning
Human-in-the-loop Reinforcement Learning
Human-Al Copilot Optimization (HACO)
Demo Video: Learning to drive in CARLA environment
Policy Dissection through Frequency Analysis
Taught by
Bolei Zhou
