CMU AI Agents course publishes lecture 12 on reinforcement learning systems

Carnegie Mellon's fall 11-768 AI Agents course, taught by Dan Fried and Graham Neubig, has published slides and video for lecture 12, "Reinforcement Learning Systems." A post by meng shao (@shao__meng) on X shares the release.

The lecture covers RL framework design, separate optimization of the inference and training sides, training-inference interaction, and practical pitfalls in agentic RL. According to the lecture material as quoted in the post, RL frameworks couple two heterogeneous workloads, training and inference, rather than sharing one computation graph.