Is the Policy Gradient a Gradient?

arXiv:1906.07073 · cs.LG, stat.ML · Submitted 2019-06-17 · Read on arXiv

cs.LG, stat.ML

Submitted: 2019-06-17

Updated: 2026-10-16

Comments: 10 pages. Corrections and clarifications to mathematical statements, Figure 1, and discussion of prior work; main result and original counterexamples retained

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Fixed Point — 2× in this paper · explained in 2 episodes
• Abundance — 1× in this paper · explained in 1 episode
• Papers — 1× in this paper · explained in 3 episodes

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks