AI Paper Atlas

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

Truncating Trajectories in Monte Carlo Policy Evaluation: an Adaptive Approach

Riccardo Poiani, Nicole Nobili, Alberto Maria Metelli, Marcello Restelli

NeurIPS 2023 · Reinforcement learning › Policy gradient and actor-critic · approach: Confounding-robust policy evaluation · 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 adaptive, iterative trajectory allocation instead of a fixed uniform scheduleMonte Carlo policy evaluation · LQGempirical MSEImproved
Use adaptive, iterative trajectory allocation instead of the robust non-adaptive scheduleMonte Carlo policy evaluation · Continuous Navigationempirical MSENo clear effect
Use adaptive, iterative trajectory allocation instead of the uniform scheduleMonte Carlo policy evaluation · Inverted Pendulumempirical MSEImproved
Use adaptive or robust trajectory allocation instead of the uniform scheduleMonte Carlo policy evaluation · Ant, γ=0.999empirical MSENo clear effect
Use adaptive or robust trajectory allocation instead of the uniform scheduleMonte Carlo policy evaluation · Ant, γ=0.99empirical MSEImproved
Use the robust schedule that truncates trajectories based only on the discount factorMonte Carlo policy evaluation · Continuous Navigationempirical MSEHurt
Allocate more samples to early interaction steps when early rewards have greater uncertaintyMonte Carlo policy evaluation · LQGempirical MSEImproved

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