Artificial Intelligence · Reinforcement Learning

Policy Gradient Methods

A topic within Reinforcement Learning, itself one of 11 topics in that field and part of Artificial Intelligence.

Reading on Policy Gradient Methods

2 works

Paper2017

Proximal Policy Optimization Algorithms

Schulman et al.

Replaces trust-region policy optimisation's constrained second-order update with a clipped surrogate objective that a handful of stochastic gradient steps can optimise, trading some theoretical guarantee for practical simplicity.

link checked 17 Sept 2026

Artificial Intelligence · Reinforcement Learning

FreeIntermediate

Paper1999

Policy Gradient Methods for Reinforcement Learning with Function Approximation

Sutton, McAllester, Singh & Mansour

Proves that policy gradient methods converge to a locally optimal policy even when the value function is approximated, as long as the approximation is compatible with the policy parameterisation.

link checked 17 Sept 2026

Artificial Intelligence · Reinforcement Learning

FreeAdvanced

Reading on Policy Gradient Methods

Proximal Policy Optimization Algorithms

Policy Gradient Methods for Reinforcement Learning with Function Approximation

Other topics in Reinforcement Learning