finds.dev

eleurent/phd-bibliography

References on Optimal Control, Reinforcement Learning and Motion Planning

View on GitHub

★ 982updated Feb 2022

// the take

A hand-organized bibliography of papers spanning optimal control, safe/robust control, bandits, reinforcement learning, and motion planning, compiled by a PhD researcher in the field. It's aimed at grad students or researchers who want a structured map of the literature rather than a scattered reading list, particularly useful for connecting RL methods to their control-theory roots.

The taxonomy is the actual value here — it groups papers by concept (e.g. risk-averse control, best-arm identification, hierarchical RL) rather than just dumping links, so you can see how subfields relate instead of guessing from titles. Entries are tagged with method acronyms (TRPO, UCRL2, MuZero) and many link to author implementations or talk videos, which saves time hunting for a reference implementation. The theory section includes regret-bound badges (setting, bound order) inline, which is a nice touch for anyone comparing RL algorithms' sample complexity at a glance.

It's a static README with no code, scripts, or tooling — just a long markdown file, so there's no way to search, filter, or query it programmatically. Last updated in February 2022, meaning it misses four years of RL/control work (no mention of anything post-2021 diffusion-based planning or recent offline RL advances). Several links already rot (personal academic pages, defunct lab sites) and there's no automated link-checking or contribution guide to keep it current. As an 'awesome-list' repo it also has no license file, which matters if anyone wants to fork and republish an updated version.

We read the README, the directory tree and a key source file in October 2026. Nobody pays to be listed. How we judge →

// at a glance

Stars
982
Forks
205
Last commit
26 Feb 2022

// nearby

If phd-bibliography isn't quite it.

All repos →