The web client now plays borealis (data/models.json), trained on the three-round
match and taking the 501-dim match view rather than a bare round. Only the actor
trunk is exported -- the critic exists to grade moves in training and never plays,
so the graph physically cannot leak the opponent's hand or the deck, which beats
promising not to call it.
The TypeScript match layer and observation mirror match.py and match_obs.py. They
have to agree to the bit: a mismatch throws nowhere, the ONNX policy just consumes
a wrong vector and plays worse for reasons nobody can see. So the port is not
trusted -- generate_match_parity_fixture.py emits 282 positions from real JAX play
(mid-round, both seats, past a roll-over, with a live carry) and the TS output is
checked against them to float32 round-off.
Match mode is a menu toggle. A seed fixes all three deals and the coin flips, so a
match stays a pure function of it. One-deal mode is unchanged from the player's
side; borealis simply sees it as round one at a carry of zero, a position it has
seen a great many times.
Two bugs found by driving the built app in a browser, both silent:
- The result card totalled the round, not the match. It read "-11 : 3" while the
match stood at -96 : 66 -- it would have named the wrong winner. It now headlines
the match total and breaks the round out beneath it.
- Game records were being rejected. The client's schema went to v2 (it now records
which model played; the old records stored the on-screen label, which stops
identifying anything once there are two models) while serve_web_with_logs.py
still only accepted v1, so every record would have 400'd into a console warning.
v1 stays accepted -- the 111 existing games are altair.
npm test and tsc were green through both. Hence web/.claude/skills/verify, which
records the recipe and the selectors so the next session drives the app instead of
re-deriving how.
.gitignore excluded the new model, which would have shipped a 404: the deploy
builds straight from the repo.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XBQKgvBbxbheiTF1AVy1Sh
The 39.3M ablation said the privileged critic hurt (switching it off won 0.5160
[0.505, 0.527]). Head to head at 131M, both sides trained identically, it says the
opposite: off *loses*, 0.4633 [0.453, 0.474]. Against league the critic-on model
scores 0.6094 and the critic-off one 0.5526.
The critic earns its keep once there is enough data to fit it -- at 39.3M the
privileged value trunk is underfit and only adds advantage noise. Defaulted back
on, with the small-scale number kept in the docstring as a warning: an ablation at
a budget you do not intend to ship can invert.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XBQKgvBbxbheiTF1AVy1Sh
The user asked why we were not simply maximising the three-round total, and they
were right. Each ply now pays the points by which it moved the running match
difference; at gamma=1 that telescopes to the final total, so the objective is
exactly the rulebook's, handed out every ply instead of once 150 plies later.
Three measurements killed the tanh design:
- Rounds are independent (corr(m1,m2)=0.004, corr(m1+m2,m3)=0.05), so a reward
linear in the total decomposes the match into three independent rounds and
carry enters the objective nowhere. The only coupling, the start-player rule,
is worth +0.73 +/- 0.84 points -- indistinguishable from zero.
- Risk attitude, the one thing tanh buys, is worthless here. A policy made to
gamble when it trails by 20 entering round three *loses* to a greedy clone over
6144 duplicate matches (0.482); gambling only at -40 breaks even (0.498). A
marginal wager buys about +1.7 sigma for -2 to -3 expected points. Ceiling on
the whole carry-conditioning idea: under one win-rate point.
- Head to head over 10,000 duplicate matches at equal compute, the linear reward
*beats* tanh(total/12): 0.5859 (CI 0.576-0.596), +20.3 points. Dropping it is
not merely free, it is better -- not because of risk, but because tanh hands a
~150-ply match one saturated +/-1 and leaves all credit assignment to the critic.
The flat carry probe was not exploration collapse: sampled play still opens 5.00
expeditions, entropy settles at 1.36 nats (3.9 effective actions), and the critic
reads carry cleanly (round-three values run -0.87 to +0.86, monotone). The signal
was there; there was nothing to buy with it.
Criterion 1 (a monotone carry response) comes off the gate accordingly -- the
optimal response barely exists in this game. carry stays in the observation: it
costs nothing and the start-player rule keys off it.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XBQKgvBbxbheiTF1AVy1Sh
Phases 2-4 land together because they all rewrite the same rollout, and doing
them in sequence would mean writing it three times.
Observation adds the four things a match policy cannot play without: carry as a
scalar *and* a binned one-hot (round three is a threshold problem -- "win by 41
or lose" plays nothing like "win by 39" -- and the old score_diff divided by
MAX_ABS_SCORE=780, squashing a decisive 50-point lead to 0.06); the round index;
whose turn it is, which the single-round observation never carried even though
the critic is trained on opponent-turn states; and the deck clock, since a round
ends on the last deck draw and players bend that parity by drawing from discard
piles. Live points per colour are split by hand / discard pile / unseen, because
a discard pile is public and recoverable.
The critic is asymmetric: it gets the opponent's hand and the deck in order, on
a separate trunk so none of it can reach the logits. A test pins that down --
perturbing the privileged input leaves the policy logits bit-identical while
moving the value. Deal luck is what makes a match-terminal reward hard to learn
from, and a state-value baseline may condition on anything action-independent.
Both seats now train. Self-play ran one network on both sides and stop_gradiented
the opponent, throwing away half of every game; each ply now emits a transition
per seat, folded into the batch so each seat keeps an independent GAE chain.
Reward is the match: rounds one and two only bank into carry, and round three
pays tanh(total / terminal_scale). Potential shaping on the running total covers
the early sparsity and anneals out.
match_eval adds the two measurements the plan turns on: duplicate match play
(same deals and coins from both seats -- self-play scores exactly 0.500 with zero
mean lead, so the mirroring cancels deal luck exactly) and the carry probe. On an
untrained net the probe is flat: 4.97 expeditions opened at a 60-point deficit
and at a 60-point lead alike. Breaking that flat line is success criterion 1.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XBQKgvBbxbheiTF1AVy1Sh
Wraps the single-round engine rather than changing it: engine.py is the rules
oracle the TypeScript client is differential-tested against, and the round
itself is unchanged by the match. Only two rules live up here, both from the
Kosmos rulebook -- three rounds decided on the summed total, and "the player who
has more points begins" the next one. That is not alternating, and it is not
what reset_from_order hardcoded, so it takes a first_player argument now.
The rulebook says nothing about an exact tie, so the starter falls back to a
coin flip. A deterministic tie-break would give one seat a standing edge in
symmetric self-play and the agent would learn to steer for it. Round one needs
no special case: carry is (0, 0) there, so the tie branch already yields the
coin, which is exactly the rulebook's arbitrary "oldest player begins".
All randomness -- three deals and three coins -- is drawn in match_reset and
stored in the state, so match_step stays deterministic and needs no PRNG key
threaded through every rollout, eval, and gate body. It also makes a mirrored
match (same deals, seats swapped, same coins) a pure seat relabel, which the
antithetic pairing later depends on.
Tests cover the deck clock (44 deck draws a round, discard draws extend it),
carry banking each round exactly once, the start-player rule across all three
branches, a fair round-one coin, mirror symmetry, and that the running total
does not jump across a round boundary -- the last one matters because potential
shaping will be built on it.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XBQKgvBbxbheiTF1AVy1Sh
rollout_steps was pinned to MAX_STEPS (400) while a round actually runs
~50 plies, and finished envs were only reset between updates. 83% of every
rollout was spent stepping already-done envs to produce masked-out zeros.
Measured at rollout_steps=400: active steps go 17.3% -> 100%, i.e. 5.8x the
learner actions per update for the same compute.
Resetting in-scan exposes three things that were previously benign:
- compute_gae bootstrapped truncated episodes from zero. That was safe only
because every episode used to terminate inside the scan; now episodes cross
the boundary, so thread V(s_T) through.
- rollout_metrics read final_env and summed rewards along the scan axis, both
of which assume one episode per slot. With several episodes per slot that
silently produces garbage, so aggregate at done boundaries instead.
- league assignments were redrawn only between updates, which would pin a slot
to one seat/opponent across every episode in a scan. Redraw them on reset.
Also anneal potential shaping against learner actions rather than padded scan
steps: the old accounting counted the dead steps, so a 5M-step anneal expired
within two updates of 250. Any earlier evidence that shaping does not help was
gathered with it effectively off.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XBQKgvBbxbheiTF1AVy1Sh
Codex deep diagnosis surfaced two real issues in our MCTS pipeline:
1. mcts.pyx::search() hardcoded prepare_simulation_batch(state, traverser, 1)
instead of respecting MctsConfig.parallel_simulations. Standalone evals
(eval_checkpoint, evaluate_with_mcts sequential path, eval_worker) all
use this entry point, so all eval-time MCTS was running 1 sim per batch
regardless of the configured 64. Training was unaffected because it
goes through interleaved_self_play._run_search_jobs which respects the
config. Fix uses min(config.parallel_simulations, sims - completed).
2. use_rollout_value defaulted to True (config.py) but was never set in
the YAML. With this, _expand_with_prior returns the heuristic rollout
value and discards network_value, so the network value head is trained
from final game scores but its outputs are never fed back into MCTS
backups. This explains why mcts/value_prediction_error stays high
despite training -- learning the value head produces no behavioral
change because MCTS never reads it.
Now setting use_rollout_value=false in default.yaml so the network value
head closes the loop. Combined with the existing Dirichlet root noise +
heuristic rollout removal, this should give the network's value learning
actual leverage on action selection.
Also: updated test_search_visit_counts_match_with_parallel_simulations
to test the correct invariant (legal-action set match + total visit
count near n_sims) rather than literal visit-count equality, which was
only true under the previous bug.
Tests: 19/19 passing.
Key changes for ISMCTS speed and correctness:
- Cython port: HeuristicBot helpers (`heuristic_cy.pyx` + new `.pxd`) and
ISMCTS searcher (`mcts.pyx`) now run as cdef. Both share a fast
unified-action path through GameState's C interface to avoid Python
round-trips on hot rollout/tree-walk paths.
- Multi-process self-play and eval: `workers.py`, `eval_worker.py`,
`interleaved_self_play.py`, plus trainer wiring with ProcessPoolExecutor
+ spawn context. Eval inside `evaluate.py` is parallel per opponent.
- ISMCTS-specific eval (`evaluate.py`) runs MCTS at decision time so the
metric matches deploy mode; `evaluation.eval_with_mcts` flag preserves
backwards-compatible policy-only eval when needed.
- Trainer logs progress per phase (self-play start/done, eval per
opponent), and value loss is now scaled by `value_scale` so policy and
value losses sit on comparable magnitudes.
- Compact info-set key (`info_set.py`) using packed-struct format and
child-key reuse during MCTS descent to cut per-step canonicalization.
Tests: 19 ISMCTS suite passing, including parity (Cython-vs-Python
sequential, batched-vs-sequential visit counts, push/pop round-trip).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Wrap AlphaZeroNet with a logits-only view so IS-MCTS training evaluation can call evaluate_strategy_network and emit the same full diagnostic metric set as Deep CFR. Adds root prior capture and per-iteration MCTS entropy, value error, and policy-vs-search KL metrics.
Tests: uv run python -m pytest tests/games/classic/ismcts/ -x; uv run python -m pytest tests/games/classic/test_deep_cfr_trainer.py -x; uv run lost-cities-ismcts train --config configs/ismcts/mini.yaml --set run.experiment_name=ismcts-metrics-smoke --set run.max_iterations=2 --set training.games_per_iter=2
Implements a proof-of-concept single-observer IS-MCTS trainer with AlphaZero-style policy/value network, determinization, replay, self-play, CLI configs, and focused tests. Mini acceptance run reaches positive random eval while keeping play_action_rate above the Deep CFR trap threshold.
Tests: uv run python -m pytest tests/games/classic/ismcts/ -x; uv run python -m pytest tests/games/classic/test_deep_cfr_trainer.py -x; uv run lost-cities-ismcts train --config configs/ismcts/mini.yaml
Mirrors the discard_only plumbing pattern. Uses HeuristicBot() (default
balanced params) and converts the bot's phase-local action to unified via
state.to_unified_action. Recursive (Cython) path was already supported
and is unchanged.
Tests: smoke run + accept/reject validators. All 59 tests pass.
Three coordinated hygiene changes; none target the diagnosed
selection-bias bottleneck. They make the codebase honestly reflect the
pure-self-play stance and reduce dashboard noise.
Bot rename (drop the unhelpful safe_ prefix; suffixes describe behaviour):
- safe_heuristic_loose -> heuristic_aggressive
- safe_heuristic -> heuristic_balanced
- safe_heuristic_strict -> heuristic_cautious
- noisy_safe -> heuristic_noisy
- passive_discard -> discard_only
Class renames in bots/: SafeHeuristicBot -> HeuristicBot,
SafeHeuristicParams -> HeuristicParams, PassiveDiscardBot -> DiscardOnlyBot,
plus loose/strict parameter constants. Backwards compatibility was dropped
intentionally per user instruction; no aliases. Active configs, docs,
scripts, tests updated. Archive directories (configs/archive,
docs/archive, runs/archive) left intact and may still reference old
names per their read-only policy. The src/.../bots/passive.py module was
renamed to discard_only.py via git mv.
Analyze plot curation (deep_cfr/analyze.py):
- Added analysis_00_core.png as the canonical daily dashboard with 10
heuristic-free metrics (loss/{advantage,strategy}; vs heuristic_cautious:
avg_score_diff0, win_rate0, avg_opened_colors, positive_expedition_rate,
bonus_expedition_rate, score_per_opened_color, policy_entropy; vs random:
win_rate0).
- Removed analysis_05_open_quality.png (bad/weak/good open rates,
recoverable score) and analysis_07_calibration.png (calibration gap,
recoverable mean) - both relied on the heuristic recoverable_score
classifier already dropped from inputs.
- Removed SELECTIVITY_PLOTS and plot_selectivity (heuristic-laden).
- SUMMARY_EVAL_METRICS no longer includes bad_open_rate or
calibration_gap.
- PlotSpec gained an opponents allowlist so the new core section can pin
a specific opponent per panel without restructuring plot_section.
Tiered evaluation cadence (EvaluationConfig):
- Added extended_opponents and extended_eval_every (default 0 = disabled).
- opponents_for_iteration(iteration) returns the core list every
eval_every and appends extended_opponents (de-duplicated) when
iteration is also a multiple of extended_eval_every.
- default.yaml now uses 3 core opponents (random, discard_only,
heuristic_cautious) every 5 iterations and 3 extended opponents
(heuristic_balanced, heuristic_aggressive, heuristic_noisy) every 50
iterations. random is the floor sanity. discard_only is the
zero-pit detector / absolute-score reference (its score is always 0,
so eval/discard_only/avg_score_diff0 directly equals the model's raw
average score). heuristic_cautious is the ceiling and the
archive-comparable benchmark used in the prior diagnostic sections.
Net eval cost reduction: roughly 50% (3 opponents x every 5 iter, plus
6 opponents x every 50 iter, vs the prior 6 x every 5).
Documented in docs/plans/deep-cfr-selectivity.md section 9.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The interleaved traversal scheduler's _regret_matching was hard-coded to
spread fallback policy uniformly across legal actions, regardless of the
configured regret_matching.all_negative_fallback. default.yaml has
shipped with all_negative_fallback: argmax_tiebreak since 618d5f8 based
on the 20-iter audit + 1000-iter empirical comparison in
docs/archive/deep-cfr-regret-fallback-audit-2026-05-07.md, but the
default scheduler was switched to interleaved in 09bbe7c, after which
the configured fallback mode silently no-op'd.
_regret_matching now takes fallback_mode and concentrates policy mass on
the lowest-index tied action when "argmax_tiebreak". Tiebreak is
deterministic; the Cython recursive traverser randomises ties using its
per-traverser RNG, which the batched policy does not have. Behaviour
matches the spirit of the recursive path (concentrate on best, do not
dilute uniformly).
Plumbed through BatchedPolicy, InterleavedTraversalConfig,
run_interleaved_traversal_batch, trainer.py, workers.py, and the
analyze_first_open_targets.py caller. Two unit tests added.
Also bumps default.yaml outcome_sampling_epsilon 0.2 -> 0.05. The
200-iter sweep in docs/plans/deep-cfr-selectivity.md section 1 showed
0.05 produced the best short-run safe_heuristic_strict score diff
(-40.01 vs -57.87 for 0.20). Recent experiments already used 0.05; the
default now matches actual experimental practice.
Neither change targets the diagnosed selection-bias bottleneck. They
align config intent with scheduler behaviour and make the default config
reproduce known-best knob settings out of the box.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
ColorSharedNetwork previously sliced the input vector into n_colors equal
chunks (input_dim // n_colors). The slice boundaries do not align with the
actual encoding layout: adjacent slices contain phase flags, hand slots,
expedition state, scores, etc. mixed together. The "color-shared" encoder
was therefore sharing weights across semantically unrelated chunks, not
across per-color blocks. The single archived run that exercised this path
(2026-05-07_092137_color_shared_attention_1000iter) was killed at iter 41
and produced no eval data, so we have no measurement of whether a real
per-color architecture would help.
Adds compute_lost_cities_color_layout(input_dim) which returns explicit
per-color and common index lists for the standard Lost Cities encoding
(n_colors=5, hand_size=8, n_ranks=9). It recognises input_dim values
171, 219, 249, 297 across derived_playability and slot_aware_playability
flag combinations.
Per-color block (39 dims when derived_playability is on): both players'
expedition state for that color, discard top, public-histogram row,
pending-discard one-hot bit, legal-action draw-pile bit, and the
derived_playability per-color block. Slot-aware features are slot-major
and stay in common.
ColorSharedNetwork.forward now indexes per-color blocks via the layout
when input_dim matches a known schema. For other dims (unit tests,
non-Lost Cities use), it falls back to chunked slicing with a UserWarning
- preserves backward compatibility for tests but makes the legacy
behaviour visible.
No fair test of the new architecture was run as part of this commit.
Documented in docs/plans/deep-cfr-selectivity.md section 7.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Audit of the Deep CFR information-state encoding identified two tiers of
non-pure features and removed both:
- Tier 3 (judgment): is_bad_open_candidate, open_risk_score,
is_safe_continuation. Same heuristic family used to label bad_open in
evaluation, embedded as model input.
- Tier 2 (projection): recoverable_score_no_bonus,
recoverable_margin_no_bonus, min_needed_to_break_even,
cards_needed_for_bonus, has_bonus_path. Mechanical but assumption-laden
("commit and play all currently-playable cards"). The no_bonus form is
asymmetric: it amplifies the immediate -20 penalty while truncating the
+20 bonus upside, biasing the model toward the same "don't open" basin
the diagnostics already flagged.
Input dim 365 -> 297. DERIVED_PLAYABILITY_PER_COLOR 19 -> 15;
SLOT_AWARE_PLAYABILITY_PER_SLOT 12 -> 6. Test shape assertions updated.
Also adds selectivity diagnostic infrastructure used to reach this point:
- traversal.outcome_unsampled_first_open_prior_alpha config field with
signed-prior overlay on unsampled first-open advantage targets (A1).
- analyze_first_open_counterfactual.py --post-policy to swap the
policy_player rollout policy and isolate selection bias (D1).
- analyze_first_open_followup.py to inspect post-forced-open behavior
(E2): same-color play vs discard counts, other-open rate, terminal
hand composition.
Findings recorded in docs/plans/deep-cfr-selectivity.md sections 3-6.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds torch.autocast(fp16) + GradScaler around _train_advantage and
_train_strategy when run.use_amp=true and device=cuda. CPU/non-CUDA
falls back to fp32 no-op. Mitigations:
- scaler.unscale_(optimizer) before grad_clip.
- nonfinite-loss guard skips overflowing batches and counts them.
- diff.float().square() in advantage loss to avoid fp16 overflow.
- strategy mask/log_softmax kept in fp32.
New metrics: amp/grad_scale, amp/nonfinite_loss_count.
Tests: AMP CUDA smoke + CPU fallback in test_deep_cfr_trainer.py.
Bench: scripts/bench_amp_trainer.py micro-benches train phases under
synthetic replay memory. smoke.yaml result is fp32 3.22ms / AMP 3.92ms
(0.82×, regression). 100-iter A/B on default.yaml deliberately
skipped: smoke regression mirrors the 2026-05-07 torch.compile
regression dynamic (dispatch overhead > kernel benefit at this model
size) and re-confirming on the same size adds no information.
Default stays run.use_amp: false. Re-enable trigger documented in
docs/performance.md: hidden_size >= 1024 or num_layers >= 6, then run
the bench script + 100-iter A/B before flipping default.
Implements the central inference server pattern: a dedicated GPU
process owns advantage/strategy/league networks, batches policy
requests across traversal workers via shared-memory tensor pool, and
returns logits. Workers route forward calls through InferenceClient /
NetworkProxy when traversal.inference_backend == "server".
Default remains traversal.inference_backend: local. The server
backend regresses iter time ~3.8× on the inspected default config
(small-model dispatch + sync-blocking traversal capping realized
batch at ~num_workers=8 instead of the bs=64-256 needed to amortize
IPC overhead). Keeping the implementation behind the flag lets us
re-enable when (a) model size grows, (b) per-worker interleaved
traversal lands, or (c) eval becomes dominant — see
docs/performance.md "Option A Bench Result and Structural Ceiling"
for the full diagnosis.
Plumbing included:
- inference_buffers.py: shared-memory tensor pool with slot
management.
- inference_client.py: per-worker client + NetworkProxy adapter for
the existing traversal.pyx call sites.
- inference_server.py: spawn-context server process with
batch-window aggregation, weight sync, shutdown sentinel.
- bench_inference_backend.py: A/B between local and server backends
with eval/checkpoint disabled.
- test_inference_server.py: round-trip and integration tests.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Cython implementation in heuristic_cy.pyx achieves ~2.55× speedup on
opponent_act_seconds (200-game eval: 59.20s → 23.24s). Original Python
implementation preserved verbatim in heuristic_py.py as the equivalence
reference. Action-sequence equivalence is verified by
test_safe_heuristic_equivalence.py against seeded game corpora.
Key implementation notes:
- File-local wraparound=True override required for negative discard
indexing; Cython global wraparound=False would segfault.
- annotation_typing=False preserves verbatim Python semantics.
- _CachedState materializes hands/expeditions/discards/deck once per
act() call — this is the dominant performance win.
Further C-array optimization of _card_value_for_me /
_card_value_for_opponent / _color_commitment / _bonus_potential is
deferred. The current 2.55× delivers most of the dense-eval future
benefit; further work is gated on actually adopting denser eval
schedules (eval_every=5, games=1000).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adopt a 5-namespace scheme so wandb groups related metrics in the
sidebar and capture-group regex (eval/(random|safe_heuristic)/win_rate0
vs eval/(?:random|safe_heuristic)/win_rate0) controls panel splitting:
- loss/{advantage,strategy}
- samples/{advantage,strategy,advantage_player_N}
- memory/{advantage,strategy,advantage_player_N}
- time/{iteration_seconds,traversal_seconds,advantage_train_seconds,
strategy_train_seconds,evaluation_seconds,memory_add_seconds,
checkpoint_seconds,batch_tensor_seconds,nodes_per_second,
advantage_player_N_sample_seconds,strategy_sample_seconds}
- traversal/{nodes,terminals,depth_cutoffs,node_limit_cutoffs,
max_depth_reached,endpoints,avg_endpoint_depth,
endpoint_depth_bucket_*,regret_fallback_*,sampled_actions}
- eval/<opponent>/<metric> (3-level so opponent can be the capture group)
`iteration` keeps no namespace (it's the wandb step axis). Internal
TraversalStats.to_dict() and benchmark.py's standalone result dict
keep their flat names — only the trainer's emitted metrics are
remapped, with the traversal_*→traversal/* translation done at
insertion into runtime_metrics.
analyze.py updated to read the new keys (PlotSpec metrics, color map,
opponent_names parser, _first_existing_eval lookup). Tests updated for
the new eval_metrics dict keys.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Make traversal progress and iteration-complete summary lines easier to
visually scan during long runs by leading with [i=N]. Drop the redundant
"iteration=N" kv from the body to keep lines short.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
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>
If eval_every is positive but max_iterations falls before the next scheduled
eval iteration (including resume cases where current_iteration is already
past the last eval boundary), log a one-time warning at run start so the
user notices the misconfiguration. We deliberately do not force an
end-of-run eval, which would distort time budgets and reproducibility.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
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 4.8