coolguyandClaude Opus 4.7
618d5f8167
The avg-strategy 1000iter file (with the recent +traversals/+LR/+LCFR
changes) is the canonical "best-known" config. Renamed it to
default.yaml so users start from a single, obvious entry point and
override one field per ablation via --set. Other 12 configs moved to
configs/archive/ — kept for historical reproduction, not for active use.
- configs/deep_cfr/{default.yaml, smoke.yaml} are the only active configs
- experiment_name shortened to "deep-cfr-default" (was a long mouthful)
- AGENTS.md examples and Project Layout section rewritten around
default.yaml; ablation example shows the override-one-field pattern
- Tests pointed at the archived slot-playability config for the legacy
reproduction assertions
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
100 lines
1.9 KiB
YAML
100 lines
1.9 KiB
YAML
run:
|
|
experiment_name: deep-cfr-default
|
|
seed: 79
|
|
max_iterations: 1000
|
|
max_minutes: null
|
|
device: cuda
|
|
use_amp: false
|
|
|
|
rules:
|
|
n_colors: 5
|
|
n_ranks: 9
|
|
min_rank: 2
|
|
n_handshakes: 3
|
|
hand_size: 8
|
|
expedition_penalty: -20
|
|
bonus_threshold: 8
|
|
bonus_amount: 20
|
|
|
|
encoding:
|
|
derived_playability: true
|
|
slot_aware_playability: true
|
|
|
|
network:
|
|
hidden_size: 512
|
|
num_layers: 3
|
|
activation: relu
|
|
|
|
traversal:
|
|
traversals_per_player: 280
|
|
max_depth: null
|
|
max_nodes_per_traversal: 1000
|
|
regret_matching_epsilon: 0.0001
|
|
outcome_sampling_epsilon: 0.2
|
|
outcome_sampling_value_clip: 500.0
|
|
outcome_unsampled_regret: zero
|
|
cutoff_value_mode: score_diff
|
|
cutoff_rollouts: 0
|
|
cutoff_rollout_policy: random
|
|
cutoff_rollout_max_steps: 300
|
|
opponent_policy: average_strategy
|
|
strategy_sample_interval: 1
|
|
store_strategy_on_traverser_nodes: true
|
|
store_strategy_on_opponent_nodes: false
|
|
num_workers: 8
|
|
worker_chunk_size: 8
|
|
progress_every_traversals: 10
|
|
endpoint_depth_bucket_width: 100
|
|
endpoint_depth_bucket_max: 1000
|
|
|
|
regret_matching:
|
|
all_negative_fallback: argmax_tiebreak
|
|
|
|
training_weighting:
|
|
mode: lcfr
|
|
|
|
self_play:
|
|
snapshot_every: 1
|
|
max_snapshots: 0
|
|
anchor_probability: 0.0
|
|
current_weight: 1.0
|
|
recent_weight: 0.0
|
|
older_weight: 0.0
|
|
anchor_weight: 0.0
|
|
recent_window: 5
|
|
|
|
optimization:
|
|
advantage_updates_per_iteration: 512
|
|
strategy_updates_per_iteration: 512
|
|
advantage_batch_size: 1024
|
|
strategy_batch_size: 1024
|
|
learning_rate: 1.0e-4
|
|
weight_decay: 0.0001
|
|
grad_clip: 1.0
|
|
|
|
memory:
|
|
advantage_capacity: 2000000
|
|
strategy_capacity: 2000000
|
|
|
|
checkpoint:
|
|
save_latest: true
|
|
save_every: 100
|
|
progress_interval_seconds: 20.0
|
|
exact_resume: false
|
|
|
|
evaluation:
|
|
eval_every: 25
|
|
games: 100
|
|
opponents:
|
|
- random
|
|
- passive_discard
|
|
- safe_heuristic
|
|
- safe_heuristic_loose
|
|
- safe_heuristic_strict
|
|
- noisy_safe
|
|
max_steps: 10000
|
|
on_max_steps: score_diff
|
|
batch_size: 64
|
|
device: trainer
|
|
num_workers: 4
|