REVIEW 5 cited by
Neural Policy Gradient Methods: Global Optimality and Rates of Convergence
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Neural Policy Gradient Methods: Global Optimality and Rates of Convergence
read the original abstract
Policy gradient methods with actor-critic schemes demonstrate tremendous empirical successes, especially when the actors and critics are parameterized by neural networks. However, it remains less clear whether such "neural" policy gradient methods converge to globally optimal policies and whether they even converge at all. We answer both the questions affirmatively in the overparameterized regime. In detail, we prove that neural natural policy gradient converges to a globally optimal policy at a sublinear rate. Also, we show that neural vanilla policy gradient converges sublinearly to a stationary point. Meanwhile, by relating the suboptimality of the stationary points to the representation power of neural actor and critic classes, we prove the global optimality of all stationary points under mild regularity conditions. Particularly, we show that a key to the global optimality and convergence is the "compatibility" between the actor and critic, which is ensured by sharing neural architectures and random initializations across the actor and critic. To the best of our knowledge, our analysis establishes the first global optimality and convergence guarantees for neural policy gradient methods.
Forward citations
Cited by 5 Pith papers
-
Randomized Advantage Transformation (RAT): Computing Natural Policy Gradients via Direct Backpropagation
RAT reformulates regularized natural policy gradients as vanilla gradients with a transformed advantage, computed efficiently via randomized block Kaczmarz iterations on on-policy data.
-
Select-then-differentiate: Solving Bilevel Optimization with Manifold Lower-level Solution Sets
Optimistic bilevel optimization with manifold lower-level minimizers is differentiable if the optimistic selection is unique, yielding a pseudoinverse hyper-gradient and a convergent HG-MS algorithm whose rate depends...
-
Optimal Sample Complexity for Single Time-Scale Actor-Critic with Momentum
Single-timescale actor-critic with STORM momentum and a recent-sample buffer achieves optimal O(ε^{-2}) sample complexity for ε-optimal policies in finite discounted MDPs.
-
Revisiting Policy Gradients for Restricted Policy Classes: Escaping Myopic Local Optima with $k$-step Policy Gradients
The k-step policy gradient converges exponentially close to the optimal deterministic policy in restricted classes, achieving O(1/T) rates under smoothness assumptions without distribution mismatch factors.
-
Interactive Inverse Reinforcement Learning of Interaction Scenarios via Bi-level Optimization
Interactive IRL is cast as bi-level optimization with an inner loop learning expert rewards and an outer loop learning interaction policies, solved by the convergent BISIRL algorithm.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.