jgrusewski 995c473ad9 docs: GPU-resident PER sum-tree design ...

Approved design for moving Prioritized Experience Replay entirely to
GPU — flat priority array with parallel prefix-sum sampling, GPU-resident
ring buffer for experiences, async loss readback. Eliminates the last
major CPU bottleneck in the DQN training loop.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-03-02 23:40:57 +01:00

..

infra

feat(infra): GPU training launcher with local/cloud routing

2026-02-23 11:19:58 +01:00

plans

docs: GPU-resident PER sum-tree design

2026-03-02 23:40:57 +01:00