AI Paper Atlas

Research map / Reinforcement learning / Policy gradient and actor-critic

Revisiting Domain Randomization via Relaxed State-Adversarial Policy Optimization

Yun-Hsuan Lien, Ping-Chun Hsieh, Yu-Shuen Wang

ICML 2023 · Reinforcement learning › Policy gradient and actor-critic · approach: Regularized scalable deep value learning

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 changedWhereMeasuredEffect
relaxed state-adversarial training (RAPPO) instead of worst-case state adversary (SCPPO)PPO · Hopper-v2, Walker2d-v2, HalfCheetah-v2 at larger attack strengthsepisode reward under state attacksImproved
relaxed state-adversarial training (RAPPO) instead of worst-case state adversary (SCPPO)PPO · Ant-v2 and Humanoid-v2 under nominal and attacked settingsepisode reward under state attacksNo clear effect
relaxed state-adversarial training (RAPPO) vs. MRPO domain randomizationPPO · environment size and gravity perturbations (0.6 to 1.4)mean reward difference vs MRPOImproved
relaxed state-adversarial training under combined attacksPPO · HalfCheetah-v2 and Humanoid-v2 combined environment + state attacksreward: HalfCheetah 3124 vs PPO 1568; Humanoid 2644 vs SCPPO 1035Improved
adaptive online relaxation parameter alpha vs fixed alpha=0.5 or linear schedules (ablation)RAPPO · HalfCheetah-v2, Hopper-v2, Walker2d-v2, Humanoid-v2 state attacksepisode reward under attack: HalfCheetah sigma=0.025: 846 vs 406 (fixed alpha)Improved
relaxed state-adversarial extension applied to SAPPO (observation adversary)SAPPO · multiple MuJoCo environments under strong attacksepisode rewardImproved
increasing the relaxation/mixing effect (larger alpha) vs worst-case onlyRAPPO · HalfCheetah-v2 nominalrewardNo clear effect

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy