reinforcement-learning-brain

Plugin reinforcement-learning-brain from marketplace agricidaniel-reinforcement-learning-brain in AgriciDaniel/reinforcement-learning-second-brain. Commands read from the repo's manifest — 1 month ago.

Skills (1)

• reinforcement-learning-brain

  Scaffold and operate Reinforcement Learning Brain, a source-cited Obsidian brain for reinforcement learning, covering fundamentals, deep RL, RLHF/RLAIF and preference optimization, evaluation, tooling, and applied best practices. Use when the user says "reinforcement-learning-brain", "Reinforcement

Subagents (6)

• classic-rl-foundations-curator

  Curator for the classic RL foundations lane of Reinforcement Learning Brain. Use when maintaining source coverage, open questions, canon folds, and deliverables for classic RL foundations. Read-mostly; records findings in the claim and source ledgers.

• deep-rl-algorithms-curator

  Curator for the deep RL algorithms lane of Reinforcement Learning Brain. Use when maintaining source coverage, open questions, canon folds, and deliverables for deep RL algorithms. Read-mostly; records findings in the claim and source ledgers.

• evaluation-and-reproducibility-curator

  Curator for the evaluation and reproducibility lane of Reinforcement Learning Brain. Use when maintaining source coverage, open questions, canon folds, and deliverables for evaluation and reproducibility. Read-mostly; records findings in the claim and source ledgers.

• llm-post-training-and-preference-optimization-curator

  Curator for the LLM post-training and preference optimization lane of Reinforcement Learning Brain. Use when maintaining source coverage, open questions, canon folds, and deliverables for LLM post-training and preference optimization. Read-mostly; records findings in the claim and source ledgers.

• reinforcement-learning-secretary

  Grounded secretary for Reinforcement Learning Brain. Use for source-cited answers about reinforcement learning (fundamentals, deep RL, RLHF/RLAIF and preference optimization, evaluation, tooling, applied practice), vault maintenance, claim review, and release hygiene. Reads the brain first, cites va

• tooling-and-engineering-practice-curator

  Curator for the tooling and engineering practice lane of Reinforcement Learning Brain. Use when maintaining source coverage, open questions, canon folds, and deliverables for tooling and engineering practice. Read-mostly; records findings in the claim and source ledgers.

Similar plugins