agentsclimarketplace

Rl policy optimization

Skill thada2402/AutoResearchClaw/researchclaw/skills/builtin/domain/rl-policy-optimization

Best practices for reinforcement learning policy optimization. Use when working on RL agents, PPO, SAC, or reward design.From its SKILL.md

Install
npx -y skills add thada2402/AutoResearchClaw --skill rl-policy-optimization

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.3 KB, 224 tokens by cl100k_base, as published. Nobody here has run it

RL Policy Optimization Best Practice

Algorithm selection:

  • Discrete actions: PPO, DQN, A2C
  • Continuous actions: SAC, TD3, PPO
  • Multi-agent: MAPPO, QMIX
  • Offline: CQL, IQL, Decision Transformer

Training recipe:

  • PPO: clip=0.2, lr=3e-4, gamma=0.99, GAE lambda=0.95
  • SAC: lr=3e-4, tau=0.005, auto-tune alpha
  • Use vectorized environments (e.g., gymnasium.vector)
  • Normalize observations and rewards
  • Log episode return, episode length, value loss, policy entropy

Evaluation:

  • Report mean +/- std over 10+ evaluation episodes
  • Use deterministic policy for evaluation
  • Compare against random policy and simple baselines
  • Report sample efficiency (return vs. env steps)

Common pitfalls:

  • Reward shaping can introduce bias
  • Seed sensitivity is HIGH — use 5+ seeds
  • Hyperparameter sensitivity — do a small sweep

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.