summaryrefslogtreecommitdiff
path: root/versus.py
diff options
context:
space:
mode:
authorhaoyuren <13851610112@163.com>2026-02-22 11:36:53 -0600
committerhaoyuren <13851610112@163.com>2026-02-22 11:36:53 -0600
commitdc8421e251f059e2136d5535bca2182af67fff75 (patch)
tree13456ff8df1ac4e4ef839f30c97916c6bda232d6 /versus.py
parent3887054e02e622ca2cb7878bc0dec63d28c7f223 (diff)
Separate CPU collect / GPU train, add training CSV log
- Game collection always on CPU, PPO update on GPU (avoids per-step transfer overhead) - Log avg_len, loss, vs_greedy win rate to CSV every 10k episodes - Add --eval_every flag for periodic evaluation Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Diffstat (limited to 'versus.py')
0 files changed, 0 insertions, 0 deletions