https://chrisliu298.ai/2026-03-02T00:00:00+00:00https://chrisliu298.ai/tags/llm/2026-03-02T00:00:00+00:00https://chrisliu298.ai/posts/off-policy-drift-in-llm-rl/2026-03-02T00:00:00+00:00https://chrisliu298.ai/posts/2026-03-02T00:00:00+00:00https://chrisliu298.ai/tags/ppo/2026-03-02T00:00:00+00:00https://chrisliu298.ai/tags/rl/2026-03-02T00:00:00+00:00https://chrisliu298.ai/tags/rlhf/2026-03-02T00:00:00+00:00https://chrisliu298.ai/tags/2026-03-02T00:00:00+00:00https://chrisliu298.ai/posts/deriving-direct-preference-optimization/2024-01-28T00:00:00+00:00https://chrisliu298.ai/posts/a-minimal-example-of-double-descent/2023-06-05T00:00:00+00:00https://chrisliu298.ai/tags/double-descent/2023-06-05T00:00:00+00:00https://chrisliu298.ai/posts/deriving-policy-gradient/2020-12-24T00:00:00+00:00https://chrisliu298.ai/news/https://chrisliu298.ai/papers/https://chrisliu298.ai/services/