coolguyandClaude Opus 4.7
acb664c873
Drop checkpoint.directory from config — config defines what an experiment is, not where its outputs go. The CLI now computes the run directory from run.experiment_name plus a timestamp, defaulting to runs/tmp/ for throwaway runs and runs/ when --keep is passed. - Remove CheckpointConfig.directory and DeepCFRConfig.checkpoint_path - DeepCFRTrainer takes run_dir: Path explicitly - CLI: add --keep boolean; --resume requires an explicit path (no shortcut) - Auto path: runs/[tmp/]<YYYY-MM-DD_HHMMSS>_<experiment_name-kebab>/ - Rename 13 configs to kebab-case; strip directory: lines; kebab their experiment_name values - Rewrite AGENTS.md training/run sections; document archive/tmp/<flat> layout, --keep, kebab-case scope - Update tests for new run_dir flow and dropped --resume shortcut Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
38 lines
585 B
YAML
38 lines
585 B
YAML
run:
|
|
experiment_name: smoke
|
|
max_iterations: 1
|
|
seed: 1
|
|
device: cpu
|
|
|
|
network:
|
|
hidden_size: 16
|
|
|
|
traversal:
|
|
traversals_per_player: 1
|
|
max_depth: 2
|
|
max_nodes_per_traversal: 64
|
|
num_workers: 0
|
|
worker_chunk_size: 1
|
|
|
|
optimization:
|
|
advantage_batch_size: 2
|
|
strategy_batch_size: 2
|
|
advantage_updates_per_iteration: 1
|
|
strategy_updates_per_iteration: 1
|
|
learning_rate: 0.001
|
|
|
|
memory:
|
|
advantage_capacity: 1000
|
|
strategy_capacity: 1000
|
|
|
|
checkpoint:
|
|
save_every: 0
|
|
save_latest: false
|
|
|
|
evaluation:
|
|
eval_every: 0
|
|
games: 2
|
|
opponents:
|
|
- random
|
|
max_steps: 10000
|