Despite remarkable progress in foundation models and end-to-end learning, today's autonomous systems still struggle to generalize reliably to new situations and often require enormous amounts of data and computational resources. * Your research will combine ideas from imitation learning, reinforcement learning, large-scale simulation, world models, and model compression to develop AI agents (across several embodiments) that can continuously improve, adapt to novel situations, and transfer effectively from simulation to reality. o extensive hands-on experience and theoretical understanding of reinforcement learning (RL), ideally with expertise in emerging behaviors, Safe RL, Offline RL, and/or Multi-agent RL, combined with exceptional Python skills and deep knowledge of industry-standard ML frameworks (e. g., PyTorch, Hugging Face, JAX, TensorFlow)
mehr