Research map / Reinforcement learning / Policy gradient and actor-critic
ULTHO: Ultra-Lightweight yet Efficient Hyperparameter Optimization in Deep Reinforcement Learning
Mingqi Yuan, Bo Li, Xin Jin, Wenjun Zeng
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add ULTHO online HP selection | PPO · Procgen (full level distribution) | aggregated mean: 40.42 -> 56.0 | Improved |
| add ULTHO online HP selection | PPO · Procgen (full level distribution) | aggregated IQM: 38.41 -> 56.41 | Improved |
| add relay optimization on top of ULTHO (ablation) | ULTHO · Procgen (full level distribution) | aggregated IQM: 56.41 -> 49.01 | Hurt |
| add relay optimization on top of ULTHO (ablation) | ULTHO · ALE-5 and stationary environments | normalized score | Improved |
| use ULTHO instead of PPO baseline | PPO · MiniGrid (sparse rewards) | return | No clear effect |
| use ULTHO | PPO · PyBullet | return | Improved |
| vary exploration coefficient c and window W (ablation) | ULTHO · Procgen | aggregated return | No clear effect |
| add more HP clusters (ablation) | ULTHO · Procgen | return | Improved |
| use ULTHO with equal 100M step budget | PPO+ULTHO · ALE-5 | normalized score | Improved |
| apply ULTHO to off-policy SAC | SAC · DMC | return | Mixed |
| use ULTHO vs TMIHF | PPO · Procgen (full level distribution) | aggregated IQM: 48.7 -> 56.41 | Improved |
Closest papers by meaning
- DPO Meets PPO: Reinforced Token Optimization for RLHF (ICML 2025 · similarity 0.87)
- A Method for Evaluating Hyperparameter Sensitivity in Reinforcement Learning (NeurIPS 2024 · similarity 0.86)
- EfficientZero V2: Mastering Discrete and Continuous Control with Limited Data (ICML 2024 · similarity 0.86)
- ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models (ICML 2024 · similarity 0.86)
- Towards General-Purpose Model-Free Reinforcement Learning (ICLR 2025 · similarity 0.86)
- Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts (NeurIPS 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
