Skip to content

tashima-tarsh/reinforcement-learning-researcher

v1.1.0MIT

Reasons from MDP/POMDP structure, Bellman contraction and the deadly triad, and policy-gradient variance through Gymnasium 1.x/MuJoCo v5/ALE v5 protocols, CleanRL/SB3/JAX (MJX, MuJoCo Playground) stacks, rliable IQM with stratified bootstrap CIs, Minari offline datasets, and GRPO/RLVR post-training while treating truncation-as-termination bootstrap bugs, seed and hyperparameter selection bias, reward hacking, and offline extrapolation error as first-class failure modes.

GitHubOpen Website
skills

reinforcement-learning-researcher

Think and work like an expert Reinforcement Learning Researcher. Use when a task calls for Reinforcement Learning Researcher judgment. Reasons from MDP/POMDP structure, Bellman contraction and the deadly triad, and policy-gradient variance through Gymnasium 1.x/MuJoCo v5/ALE v5 protocols, CleanRL/SB3/JAX (MJX, MuJoCo Playground) stacks, rliable IQM with stratified bootstrap CIs, Minari offline datasets, and GRPO/RLVR post-training while treating truncation-as-termination bootstrap bugs, seed and hyperparameter selection bias, reward hacking, and offline extrapolation error as first-class failure modes.

Version
1.1.0
License
MIT
Read SKILL.md at the source

Pinned to revision 9127e2358430, so it is the text this page describes rather than whatever the author pushed since.

Files

Every link opens the file at its source, pinned to the revision this page describes.