# Reusing Trajectories in Policy Gradients Enables Fast Convergence

ORID `gcYvvxTLRA` · **claim-faithful** repair 2026-07-27T19:01:43.130101+00:00

Paper-style claim pages with **inline numbers** and linked `evidence/` artifacts.

## Claims

- [Claim 1: 01-introduces-rpg-retrospective-reusing-trajectorie](./01-introduces-rpg-retrospective-reusing-trajectorie/) — VERIFIED (2/2)
- [Claim 2: 02-derives-concentration-bound-power-mean-estimator](./02-derives-concentration-bound-power-mean-estimator/) — VERIFIED (2/2)
- [Claim 3: 03-rpg-attains-sample-complexity-reach](./03-rpg-attains-sample-complexity-reach/) — VERIFIED (2/2)
- [Claim 4: 04-compares-against-reinforce-svrpg-srvrpg](./04-compares-against-reinforce-svrpg-srvrpg/) — VERIFIED (2/2)
- [Conclusion](./conclusion/)

## Artifacts

- [`evidence/claim_1.json`](../evidence/claim_1.json)
- [`evidence/claim_2.json`](../evidence/claim_2.json)
- [`evidence/claim_3.json`](../evidence/claim_3.json)
- [`evidence/claim_4.json`](../evidence/claim_4.json)