41554 blogs · [ { "id": "01a08765-12ee-730a-8ccc-5e8db3e46fb1", "title": "Oldies but goodies: ODE solvers", "url": "https://cruxponent.com/post/ode/", "published_at": "2026-08-22T00:00:00+00:00" }, { "id": "01a08765-12ee-730a-8ccc-5e8db4445e23", "title": "Off-Policy Policy Evaluation", "url": "https://cruxponent.com/post/off_policy_eval/", "published_at": "2026-06-15T00:00:00+00:00" }, { "id": "01a08765-12ee-730a-8ccc-5e8db4ed5a7f", "title": "Post-Training is a Contextual Bandit", "url": "https://cruxponent.com/post/rl_4_llm/", "published_at": "2026-04-29T00:00:00+00:00" }, { "id": "01a08765-12ee-730a-8ccc-5e8db5e89991", "title": "Control in (Generally) Regularised MDPs", "url": "https://cruxponent.com/post/regularised_mdp/", "published_at": "2025-12-05T00:00:00+00:00" }, { "id": "01a08765-12ee-730a-8ccc-5e8db62d284b", "title": "Information Theory Cheat-Sheet", "url": "https://cruxponent.com/post/inf_theory/", "published_at": "2025-10-13T00:00:00+00:00" }, { "id": "01a08765-12ee-730a-8ccc-5e8db6a70f01", "title": "A PPO Saga", "url": "https://cruxponent.com/post/ppo_saga/", "published_at": "2025-08-12T00:00:00+00:00" }, { "id": "01a08765-12ee-730a-8ccc-5e8db730bc7a", "title": "Variational Inference in POMDPs", "url": "https://cruxponent.com/post/vi_and_pomdp/", "published_at": "2025-06-20T00:00:00+00:00" }, { "id": "01a08765-12ee-730a-8ccc-5e8db7f0c499", "title": "Successor States and Representations (2/3)", "url": "https://cruxponent.com/post/successor_2/", "published_at": "2025-05-03T00:00:00+00:00" }, { "id": "01a08765-12ee-730a-8ccc-5e8db89f2b7d", "title": "Average Reward Control (1/2)", "url": "https://cruxponent.com/post/mdp_average/", "published_at": "2025-04-09T00:00:00+00:00" }, { "id": "01a08765-12ee-730a-8ccc-5e8db8cac471", "title": "Successor States and Representations (1/3)", "url": "https://cruxponent.com/post/successor_1/", "published_at": "2025-02-24T00:00:00+00:00" } ] posts Claim your blog

Blog · corpus.blog/blogs/cruxponent.com/posts