AI Paper Atlas

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

Ordering-based Conditions for Global Convergence of Policy Gradient Methods

Jincheng Mei, Bo Dai, Alekh Agarwal, Mohammad Ghavamzadeh, Csaba Szepesvari, Dale Schuurmans

NeurIPS 2023 · Reinforcement learning › Policy gradient and actor-critic · approach: Variance-reduced policy gradients · 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
Swap columns 2 and 3 of the feature matrix (Example 1 to Example 2), which breaks reward order preservation (ablation)Softmax PG · 4-action bandit, log-linear policylimit of expected reward: 9 -> 8Hurt
Swap columns 1 and 2 of the feature matrix (Example 1 to Example 3), which breaks optimal action preservation (ablation)NPG · 4-action bandit, log-linear policylimit of expected reward: 9 -> 8Hurt
Swap columns 1 and 2 of the feature matrix (Example 1 to Example 3) (ablation)Softmax PG · 4-action bandit, log-linear policylimit of expected reward: 9 -> 9No clear effect
Swap columns 2 and 3 of the feature matrix (Example 1 to Example 2) (ablation)NPG · 4-action bandit, log-linear policylimit of expected reward: 9 -> 9No clear effect
Use a feature matrix with non-zero approximation error (14.2338) instead of requiring zero approximation errorSoftmax PG and NPG · Example 1global convergence: 9No clear effect
Violate non-domination condition on features (Proposition 2) even with linearly realizable reward (ablation)Softmax PG · K=3, d=2 counterexampleglobal convergenceHurt
Make r-hat(a*) equal to r-hat(2) so strict inequality of optimal action preservation fails (ablation)NPG · Example 4global convergenceHurt
Remove reward order preservation on Example 5 (no order-preserving w exists) (ablation)Softmax PG · Example 5limit of expected reward: 9No clear effect
Remove reward order preservation on Example 5 (ablation)NPG · Example 5global convergenceHurt
Run NPG with optimal action preservation satisfiedNPG · Example 1convergence rateImproved
Run Softmax PG for 10^8 iterationsSoftmax PG · Example 1convergence rate: slope approaches -1Mixed

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