Tim Franzmeyer

benchmark evaluation (1) sequential decision-making (1) imitation learning (1) domain adaptation (1) cross-domain learning (1) policy learning (1) adversarial training (1) llm evaluation (1) inverse reinforcement learning (1) mutual information (1) web search (1) reward function (1) diffusion model (1) policy transfer (1) trajectory generation (1) real-world datum (1) large language model (1) test data contamination (1) cross-domain imitation learning (1) reward extraction (1)