AI Paper Atlas

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

Distributional Model Equivalence for Risk-Sensitive Reinforcement Learning

Tyler Kastner, Murat A Erdogdu, Amir-massoud Farahmand

NeurIPS 2023 · Reinforcement learning › Policy gradient and actor-critic · approach: Distributional value learning · 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
plan in a statistical functional equivalent model instead of a proper value equivalent modelCVaR value iteration · Tabular environments (Four Rooms, Frozen Lake, Windy Cliffs)CVaR(0.5) of returnsImproved
augment QR-DQN-based CVaR algorithm with a statistical functional equivalent modelCVaR QR-DQN · Option trading, 10,000 environment interactionsCVaR of returnsImproved
augment with a proper value equivalent model instead of the statistical functional modelCVaR QR-DQN · Option tradingCVaR of returns at low CVaR levelsHurt
use statistical functional equivalent model instead of MLE model as distracting dimensions increaseModel-based CVaR planning · Option trading with 2 and 6 distracting dimensionsCVaR of returnsImproved
use statistical functional equivalent model instead of MLE model under constrained transition matrix rankModel-based CVaR planning · Tabular environments with rank-constrained modelCVaR of returnsImproved

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