H
Howardism
Howardism · Vol. 03Plate I · No. 01

Reinforcement Learning, tagged.

Notes11TagReinforcement LearningOldest15 Jul 2026Newest24 Sept 2026

Every article tagged reinforcement learning, newest first.

  1. C01
    Anchored Bellman-Residual Correction (BRACE)
    Reinforcement LearningPost TrainingAgentic Rl+3
    · 14′
  2. C02
    ExecCritic: Learn to Test, Test to Improve
    Reinforcement LearningPost TrainingCode Generation+4
    · 16′
  3. C03
    Staleness–Learning-Rate Scaling
    Reinforcement LearningPost TrainingAgentic Rl+2
    · 18′
  4. C04
    RL from Execution Feedback (RLEF)
    Reinforcement LearningPost TrainingCode Generation+2
    · 16′
  5. C05
    Offline Multi-Step Tool-Use RL (SWiRL)
    Reinforcement LearningPost TrainingTool Use+2
    · 12′
  6. C06
    Error-Penalized Abstention Training
    Post TrainingReinforcement LearningReward Design+2
    · 22′
  7. C07
    Turn-Level Credit Assignment
    Reinforcement LearningPost TrainingAgentic Rl+2
    · 20′
  8. C08
    Asynchronous RL for LLMs
    LLM ArchitectureReinforcement LearningPost Training+2
    · 34′
  9. E09
    GLM (Z.AI)
    EntityLLM ModelOpen Weights+1
    · 19′
  10. C10
    Group Relative Policy Optimization (GRPO)
    LLM ArchitectureReinforcement LearningPost Training+1
    · 34′
  11. C11
    Single-Rollout Optimization
    LLM ArchitectureReinforcement LearningPost Training+2
    · 19′