Gunjan Dhanuka — Learning Notes

policy-gradient

6 items with this tag.

  • Sep 02, 2026

    Advantage Function

    • reinforcement-learning
    • advantage
    • variance-reduction
    • policy-gradient
    • rl-for-llms
  • Sep 02, 2026

    Policy Gradient Theorem

    • reinforcement-learning
    • policy-gradient
    • score-function
    • rlhf
    • rl-for-llms
  • Sep 02, 2026

    PPO (Proximal Policy Optimization)

    • rl
    • ppo
    • trust-region
    • policy-gradient
    • rlhf
    • importance-sampling
    • rl-for-llms
  • Sep 02, 2026

    REINFORCE

    • reinforcement-learning
    • policy-gradient
    • reinforce
    • monte-carlo
    • rlhf
    • rl-for-llms
  • Sep 02, 2026

    02 · Policy Gradients

    • reinforcement-learning
    • policy-gradient
    • reinforce
    • baselines
    • variance-reduction
    • rlhf
  • Sep 02, 2026

    04 · PPO

    • rl
    • ppo
    • trpo
    • trust-region
    • policy-gradient
    • rlhf
    • importance-sampling

Created with Quartz v5.0.0 © 2026

  • Personal site
  • Research
  • Field notes
  • Source