AI Paper Atlas

Research map / Bandits and online learning / RL theory and MDPs

Learning in Non-Cooperative Configurable Markov Decision Processes

Giorgia Ramponi, Alberto Maria Metelli, Alessandro Concetti, Marcello Restelli

NeurIPS 2021 · Bandits and online learning › RL theory and MDPs · approach: Non-stationary and structured MDPs · 2 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 AfOCL (plausible-action optimism) instead of UCB1configurator learning · Configurable Gridworld (M=10, 30)cumulative regretImproved
add noisy agent-reward feedback (RfOCL instead of AfOCL)AfOCL · Configurable Gridworld (M=10, 30)cumulative regretImproved
violate Assumption 1 with non-ergodic deterministic optimal policiesRfOCL vs AfOCL · Gridworld without ergodicity (3 configurations)cumulative regretNo clear effect
use AfOCL and RfOCL instead of UCB1 in non-ergodic settingUCB1-tuned · Gridworld without ergodicitycumulative regretImproved
use AfOCL and RfOCL instead of UCB1UCB1 · Student-Teacher (M=40, 60, 100)cumulative regretImproved
increase number of configurations M from 40 to 100RfOCL relative to AfOCL · Student-Teachercumulative regret gapImproved

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