AI Paper Atlas

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

Propagating Uncertainty in Reinforcement Learning via Wasserstein Barycenters

Alberto Maria Metelli, Amarildo Likmeta, Marcello Restelli

NeurIPS 2019 · Reinforcement learning › Policy gradient and actor-critic · approach: Temporal-difference and discounting theory · 7 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 Wasserstein-barycenter Q-posteriors (G-WQL, P-WQL) instead of classic Q-learning with Boltzmann explorationWQL · Taxi, Six Arms, River Swimonline average returnImproved
use WQL instead of Bootstrapped Q-learning with double estimatorWQL · tabular tasks (Taxi, Chain, Six Arms)online average returnImproved
use WQL instead of BQL on River SwimWQL · River Swimonline average returnNo clear effect
use WQL instead of Delayed Q-learningWQL · all tabular tasksonline average returnImproved
use WQL instead of MBIE-EBWQL · Chain and RiverSwim vs SixArmsonline average returnMixed
pair optimistic exploration (OX) with optimistic estimator (OE) rather than mismatched estimator (ablation)G-WQL · Six Armsonline average returnImproved
pair posterior sampling exploration (PX) with posterior estimator (PE) rather than OE (ablation)G-WQL · Six Armsonline average returnImproved
choice of exploration strategy and maximum estimator (ablation)WQL variants · tabular tasksonline average returnMixed
use Particle DQN instead of Double DQN and Bootstrapped DQNPDQN · Asterix, Endurooffline average returnImproved
use Particle DQN instead of DDQN and BDQN on BreakoutPDQN · Breakoutoffline average returnNo clear effect
narrow the particle initialization interval (ablation)PDQN · Atarilearning speed / final performanceMixed

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