AI Paper Atlas

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

Adaptive Temporal-Difference Learning for Policy Evaluation with Per-State Uncertainty Estimates

Carlos Riquelme, Hugo Penedones, Damien Vincent, Hartmut Maennel, Sylvain Gelly, Timothy A Mann, Andre Barreto, Gergely Neu

NeurIPS 2019 · Reinforcement learning › Policy gradient and actor-critic · approach: Temporal-difference and discounting theory · 8 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
adaptively switch between TD and MC per state vs TD(lambda=0.75)Adaptive TD · Atari Pong low-dataMSVE: 30\%Improved
adaptive switching vs TD(lambda=0.75)Adaptive TD · Atari Space InvadersMSVE: 20\%Improved
Adaptive TD vs raw TD in Labyrinth-2D high-data regimeAdaptive TD · Labyrinth-2DMSVEImproved
Adaptive TD vs MC in Labyrinth-2D low-data regimeAdaptive TD · Labyrinth-2DMSVEImproved
MC ensemble of 3 networks vs single MC networkMC · AtariMSVEImproved
Adaptive TD vs auxiliary MC ensembleAdaptive TD · AtariMSVEImproved
Adaptive TD vs raw TD in AtariAdaptive TD · AtariMSVENo clear effect
TD(lambda=0.75) as fixed choiceTD(lambda) · Labyrinth-2DMSVEImproved
TD(lambda=0.75) as fixed choiceTD(lambda) · AtariMSVEHurt
Adaptive TD vs TD in Mountain CarAdaptive TD · Mountain CarMSVEImproved

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