AI Paper Atlas

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

Taylor TD-learning

Michele Garibbo, Maxime Robeyns, Laurence Aitchison

NeurIPS 2023 · Reinforcement learning › Policy gradient and actor-critic · approach: Temporal-difference and discounting theory · 1 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 Taylor TD updates instead of sample-based TD updatesTD-learning · Control tasks except Pendulum (batch updates)update varianceImproved
use Taylor TD updates instead of sample-based TD updatesTD-learning · Pendulum (4-dimensional)update varianceNo clear effect
measure Taylor TD variance at no training, 5000 and 50000 steps (ablation)Taylor TD · Half-Cheetah-v2update varianceImproved
replace sample-based expected updates with Taylor expansion (TaTD3 vs Sample-based Expected-TD3) (ablation)TaTD3 · Half-Cheetah, Walker2d, Humanoidaverage returnImproved
replace sample-based expected updates with Taylor expansion (ablation)TaTD3 · Humanoid-v2average returnImproved
replace sample-based expected updates with Taylor expansion (ablation)TaTD3 · Pendulum-v1average returnNo clear effect
compare TaTD3 with MAGETaTD3 · Hopper-v2, Walker2d-v2, Ant-v2average returnImproved
compare TaTD3 with MBPOTaTD3 · Humanoid-v2average returnImproved
compare TaTD3 with Dyna-TD3 and SACTaTD3 · six continuous control tasksaverage returnImproved
add state/action perturbation expected-update estimation (Sample-based Expected-TD3 vs Dyna-TD3) (ablation)TD3 with model · continuous controlaverage returnHurt
increase data dimension in toy example (ablation)Taylor expansion vs sample-based · toy function approximationbenefit of Taylor expansionImproved

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