AI Paper Atlas

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

Challenging Common Assumptions in Convex Reinforcement Learning

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

NeurIPS 2022 · 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
Optimize the finite-trials objective over empirical state distributions instead of the infinite-trials objective over their expectationConvex RL · Pure explorationstate entropyImproved
Optimize the finite-trials objective over empirical state distributions instead of the infinite-trials objective over their expectationConvex RL · Risk-averse RLCVaRImproved
Optimize the finite-trials objective over empirical state distributions instead of the infinite-trials objective over their expectationConvex RL · Imitation learningKL divergence to expert distributionImproved
Use the finite-trials objective rather than the infinite-trials objectiveConvex RL · Finite-trials convex RLapproximation error: 4 L T \sqrt{ \frac{2 S \log ( 4T / \delta)}{n}}Mixed
Use history-dependent policies instead of restricting to stationary policiesSingle-trial convex RL · Pure explorationstate entropyImproved
Use history-dependent policies instead of restricting to stationary policiesSingle-trial convex RL · Risk-averse RLCVaRImproved
Use history-dependent policies instead of restricting to stationary policiesSingle-trial convex RL · Imitation learningKL divergence to expert distributionImproved
Replace the state with the full trajectory history in an extended MDPSingle-trial convex RL · Finite-horizon convex MDPpolicy-space size: |S_ℓ| > S^THurt
Replace the nonlinear convex objective with a linear reward objectiveConvex RL · Linear RL, any number of trialsoptimal-policy equivalenceNo clear effect

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