AI Paper Atlas

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

Convex Reinforcement Learning in Finite Trials

Mirco Mutti, Riccardo De Santi, Piersilvio De Bartolomeis, Marcello Restelli

JMLR 2023 · Reinforcement learning › Policy gradient and actor-critic · approach: Model-based RL with guarantees

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
optimize the single-trial utility (non-Markovian deterministic policy) instead of the infinite-trials utilityConvex RL policy · Pure exploration, state entropy (T=6)entropy H(d)Improved
optimize the single-trial utility instead of the infinite-trials utilityConvex RL policy · Risk-averse RL, CVaR (T=5, alpha=0.4)CVaR utilityImproved
optimize the single-trial utility instead of the infinite-trials utilityConvex RL policy · Imitation learning, KL to expert (T=12)KL(d||dE)Improved

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