AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Online Reinforcement Learning for Mixed Policy Scopes

Junzhe Zhang, Elias Bareinboim

NeurIPS 2022 · Reinforcement learning › Visual and representation RL · approach: Inferring decision-making from behavior · 0 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
Use causal Thompson sampling (c-ts*) instead of standard Thompson sampling over all deterministic policiesCAUSAL-TS* · Simulation Experiment 1 (Fig. 1 diagram, 100 random SCMs)cumulative regretImproved
Use simplified mixed scope (ts*) instead of all deterministic policies (ts) (ablation)Thompson sampling · Simulation Experiment 1cumulative regretNo clear effect
Use randomized trials (rct) instead of adaptive learnersonline learner · Simulation Experiment 1cumulative regretHurt
Use causal Thompson sampling (c-ts*) instead of ts and ts*CAUSAL-TS* · Simulation Experiment 2 (cardiovascular diagram, 100 random SCMs)cumulative regretImproved
Use simplified mixed scope (ts*) instead of all deterministic policies (ts) (ablation)Thompson sampling · Simulation Experiment 2cumulative regretNo clear effect
Use randomized trials (rct)online learner · Simulation Experiment 2cumulative regretHurt
Use causal Thompson sampling (c-ts*) instead of other learnersCAUSAL-TS* · Simulation Experiment 3 (Fig. 2 diagram, 100 random SCMs)cumulative regretImproved
Prune redundant policy scope S1,2 via graphical conditions (ts* vs ts) (ablation)Thompson sampling · Simulation Experiment 3cumulative regretImproved
Use randomized trials (rct)online learner · Simulation Experiment 3cumulative regretHurt
Refine mixed scope by removing redundant scope S1,2 (S to S*)CAUSAL-UCB* · Fig. 2 diagram, regret boundregret boundImproved
Use minimal reduction C* of c-collection for canonical SCMscanonical SCM parametrization · Fig. 1a diagramcardinality of U2: 48Improved

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