AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Improving Generalization in Reinforcement Learning with Mixture Regularization

KAIXIN WANG, Bingyi Kang, Jie Shao, Jiashi Feng

NeurIPS 2020 · Reinforcement learning › Visual and representation RL · approach: Robust visual encoders for RL · 47 citations (OpenAlex)

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
Train PPO with mixreg, mixing observations and their supervision signalsPPO · Procgen 500-level generalizationzero-shot testing performanceImproved
Train Rainbow with mixreg, mixing observations and their supervision signalsRainbow · Procgen 500-level generalizationzero-shot testing performanceImproved
Combine mixreg with other methodsPPO on Starpilot · Procgen Starpilot, 500-level generalizationtesting performanceImproved
Use cutout-color, random crop, or random convolution instead of mixregPPO · Procgen 500-level generalizationzero-shot testing performanceMixed
Add mixregPPO with different model sizes · Procgen 500-level generalizationzero-shot testing performanceImproved
Add mixregPPO on Fruitbot · Procgen Fruitbot, 500-level generalizationsample efficiencyImproved
Mix observations without mixing the associated supervision signals (ablation)PPO mixreg · Procgen gameszero-shot testing performanceNo clear effect
Add interpolation of the associated supervision signals to observation mixing (ablation)PPO mixreg · Procgen gamespolicy generalizabilityImproved
Use a larger beta-distribution parameter, such as α=1.0, to sample mixing coefficients (ablation)Mixreg · Procgen environmentstesting performanceHurt

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