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>
Remove legacy aliases, rename max_hours to max_minutes, collapse the
four checkpoint save flags into save_every + save_latest, and change
defaults to safer values (opponent_policy=self_play_league,
device=auto, eval_every=50, max_depth=null). Migrate all archived
yaml configs and tests to the new schema.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Mirror Deep CFR training metrics to W&B via a new WandbRunTracker
wired through CompositeRunTracker; wandb is an optional extra so
default installs and runs stay unchanged. Train CLI gains
--wandb/--wandb-project/--wandb-mode/--wandb-name/--wandb-tag, and
train() now closes the tracker in a finally block so runs finalize
even on early exit.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Add network.kind field to config (mlp/color_shared)
- Implement ColorSharedNetwork that:
- Splits input into 5 equal color blocks
- Encodes each block with shared weights
- Pools with mean/max aggregation
- Concatenates pooled embeddings with remainder
- Outputs same action logits as MLP
- Add ColorAttention for optional self-attention over color embeddings
- Add network.color_attention_layers and color_attention_heads config
- Maintain full backward compatibility (default kind=mlp)
- Add 28 comprehensive tests covering all architectures
Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
coolguyandClaude Opus 4.7