AI Paper Atlas

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

Surrogate Objectives for Batch Policy Optimization in One-step Decision Making

Minmin Chen, Ramki Gummadi, Chris Harris, Dale Schuurmans

NeurIPS 2019 · Reinforcement learning › Policy gradient and actor-critic · approach: Model-based RL with guarantees · 12 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
Replace direct expected-reward (R-hat) objective with reverse KL surrogatePolicy training, full feedback · CIFAR-10 full reward feedbacktest error %: 19.9% -> 10.7%Improved
Replace log-likelihood with reverse KL surrogatePolicy training, full feedback · CIFAR-10 full reward feedbacktest error %: 10.4% -> 10.7%No clear effect
Use composite surrogate instead of direct R-hat on random-behavior bandit dataPolicy training, bandit feedback · MNIST and CIFAR-10 uniform behavior policytest errorImproved
Use composite surrogate instead of direct R-hat on benchmark bandit dataCIFAR-10 bandit data of [14] · CIFAR-10 bandit feedback (50k to 250k)test error %: 8.71 -> 8.34 (50k); 6.66 -> 6.36 (250k)Improved
Add squared-error term and R-hat mix to reverse KL (composite vs reverse KL alone) (ablation)Surrogate objective · CIFAR-10 bandit feedback (50k)test error %: 16.00 -> 8.34Improved
Use composite surrogate instead of R-hat on CriteoLinear policy on Criteo · Criteo testimportance-sampled reward x10^4: 51.72 ± 1.42 -> 55.09 ± 2.86Improved
Use reverse KL alone instead of R-hat on Criteo (ablation)Linear policy on Criteo · Criteo testimportance-sampled reward x10^4: 51.72 ± 1.42 -> 52.30 ± 0.83No clear effect
Use squared error alone instead of log-likelihood or surrogate (ablation)Policy training, full feedback · MNIST and CIFAR-10test errorHurt

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