The final seven lectures move from exploration and theoretical limits through two review lectures to advanced exploration, multitask RL, and unresolved research problems.
Five assignments move from CPU-friendly imitation learning to H100-based LLM RL and six-hour offline-RL runs; self-learners should use three compute tiers instead of copying the entire enrolled workflow.
The first four lectures move from behavioral cloning to MDPs; HW1 turns distribution shift into an observable failure through MSE policies, DAgger, and flow matching.
L11–18 connect control as inference, LLM RL, model-based RL, and offline RL, with HW4 and HW5 providing two compute-intensive implementations.
L5–10 build the deep-RL core through policy- and value-based routes; HW2 is CPU-friendly, while HW3's Atari and HalfCheetah runs can require hours of GPU time.
Spring 2026 CS185/285 publishes slides for 25 lectures, nine discussion units, five assignments, and starter code; lecture recordings are public on the RAIL YouTube channel, but Ed, Gradescope, and office hours remain enrolled-only, while HW4 defaults to an H100, so this is not a zero-cost open course.
Units 15–18 place NLP models inside perception, reasoning, tool, and environment loops; the question shifts from next-token prediction to allocating inference compute and validating multi-step action.
The first four units make text countable, representable, and classifiable; A1 then moves from n-grams and perceptrons to an NBOW MLP.
CS288 moves from n-grams to RAG, reasoning, and agents through 18 public slide units and three assignments; Berkeley-only recordings make this an A3 materials route, not a public video course.
Units 08–12 turn a base model into an interactive system: pre-training establishes capability, post-training shapes behavior, and generation plus evaluation determine how outputs are used.
Units 13–14 connect models to external knowledge; A3 requires data collection, QA annotation, indexing, and ablations under CPU and latency constraints.
Units 05–07 move from recurrent state to encoder-decoder models, then rewrite the information path with attention and Transformer blocks.
07-380 Fall 2026 is the first offering of CMU's new AI II: 26 lectures from logic, planning and optimization to probabilistic graphs and generative systems. As of the 2026-09-29 course site, the Lec1–9 slides, PR1–6 notes, Rec1–5 (with solutions) and HW1–3 are public, and this site now has 14 lecture-by-lecture guides for them. Slides after Lec10, HW4–7 and the final project are not out yet, so the course as a whole is still A2.
HW1 is written and programming work: mathematical and CS foundations followed by a majority-vote classifier.
HW2 moves from hand-calculated entropy and mutual information to an end-to-end tree learner, predictor, and evaluator.
HW3 is written work: a decision-tree review followed by K-NN, Perceptron, and Linear Regression through inductive bias, errors, and model selection.
HW4 joins probabilistic interpretation, cross-entropy gradients, and implementation into one traceable training pipeline.
HW5 avoids automatic differentiation so learners must track forward shapes, caches, and backward gradients themselves.
HW6 combines generalization, MLE/MAP, probabilistic learning, fairness metrics, and social impact in one written assignment about assumptions and tradeoffs.
HW7 builds on HW5 backpropagation to address deep-model architecture and training failures, emphasizing diagnosis over merely adding layers.