Move 53 DQN source files + gpu_replay_buffer from ml into standalone
ml-dqn crate. The ml crate's dqn module is now a thin re-export layer
(`pub use ml_dqn::*`) plus two bridge files (trainable_adapter.rs,
stress_testing.rs) that depend on ml-internal types.
Key changes:
- ml-dqn: 45 modules, 334 tests, compiles standalone
- ml: depends on ml-dqn, re-exports via dqn/mod.rs
- DQN.config: pub(crate) → pub for cross-crate access
- DQNAgent checkpoint methods moved into ml-dqn
- gpu_replay_buffer moved from cuda_pipeline/ to ml-dqn
- 8 dead-code files removed (never declared in mod.rs)
Net: -30,648 lines from ml crate. Workspace: 0 errors.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Move Sharpe ratio metrics and SIMD performance module to ml-core.
These only depend on MLError which is already in ml-core.
Add approx = "0.5" to ml-core dev-dependencies for Sharpe tests.
Skip observability/ (needs prometheus dep — stays in ml).
Test counts: 271 ml-core + 2487 ml = 2758 total, 0 failures
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Move 6 shared modules (~2.3K lines) from ml to ml-core:
- trading_action.rs (TradingAction enum)
- action_space.rs (action masking, re-exports)
- xavier_init.rs (Xavier/Glorot weight initialization)
- mixed_precision.rs (AMP utilities, FP16/BF16)
- order_router.rs (deterministic order routing)
- portfolio_tracker.rs (portfolio state tracking)
With TradingAction now in ml-core alongside FactoredAction, the
FactoredActionExt extension trait is eliminated entirely —
from_trading_action()/to_trading_action() become inherent methods
on FactoredAction. This removes the need for `use FactoredActionExt`
imports in reward.rs, gae.rs, and trajectories.rs.
Test counts: 250 ml-core + 2508 ml = 2758 total, 0 failures
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Move memory_optimization/ (4.6K lines, 7 files) from ml to ml-core
- Move batch_size_resolver.rs to ml-core (now both deps in same crate)
- Add tempfile to ml-core dev-dependencies (qat tests)
- Re-export both modules from ml facade
- Keep checkpoint/ in ml (model_implementations.rs has model-specific deps)
185 ml-core tests + 2573 ml tests = 2758 total, 0 failures
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Move safety/ module (6.5K lines) from ml to ml-core (self-contained)
- Keep security/ in ml (depends on ensemble::EnsembleDecision)
- Move From<ProductionTrainingError> for MLSafetyError to ml (cross-crate)
- Rename Real-prefixed inference types to proper names:
RealInferenceError → InferenceError
RealInferenceConfig → InferenceConfig
RealPredictionResult → InferencePrediction
RealNeuralNetwork → NeuralNetwork
RealMLInferenceEngine → MLInferenceEngine
- Re-export safety from ml facade for backward compatibility
129 ml-core tests + 2629 ml tests = 2758 total, 0 failures
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Move optimizers, gradient_accumulation, gradient_utils, cuda_compat,
tensor_ops, and gpu (device config, capabilities, memory profiling) to
ml-core. These are shared compute primitives used by all models.
Also commit module files for core types (common, config, error, model,
traits, types) that were moved from ml to ml-core in task 5a but left
staged without being committed.
Notable changes:
- resolve_batch_size() stays in ml (new batch_size_resolver module)
because it depends on memory_optimization::auto_batch_size which
has not yet moved to ml-core
- FactoredAction legacy bridge converted from inherent impl to
extension trait (FactoredActionLegacy) since FactoredAction is now
defined in ml-core, not ml
- candle-optimisers added to ml-core dependencies (needed by Adam)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Move all inline type definitions from ml/src/lib.rs to ml-core:
MLError, MLResult, Trade, MarketRegime, HealthStatus, Features,
MLModel trait, ModelRegistry, ParallelExecutor, LatencyOptimizer,
TrainingMetrics, ValidationMetrics, InferenceResult, ModelMetadata.
Dedup: consolidate ConfigError{reason}/ConfigurationError(msg) into
single ConfigError(String) tuple variant (was 2 variants, 174 refs).
Cleanup: convert create_hft_* free functions to associated methods
(HFTPerformanceProfile::ultra_low_latency(), ParallelExecutor::hft()).
ml facade re-exports via `pub use ml_core::*`.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Move mixed_precision, xavier_init, portfolio_tracker, action_space,
order_router from dqn/ to ml/src/ root. Extract TradingAction enum
from dqn/agent.rs to standalone trading_action module. Re-export
from dqn/mod.rs for backward compatibility.
These modules are shared infrastructure used by PPO, trainers,
hyperopt, and ensemble — not DQN-specific.
Test results: 2757 passed, 0 failed, 25 ignored (unchanged).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add 5 empty sub-crates (ml-core, ml-dqn, ml-ppo, ml-supervised, ml-infra)
to workspace. Modules will be moved from monolithic ml crate in subsequent
tasks.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Three bugs in the GPU experience collection hot path:
1. gpu_batch_to_experiences() had hardcoded state_dim=43 but the CUDA kernel
outputs states at the ALIGNED dimension (56 with OFI, 48 without). After
sample 0, every replay buffer entry had corrupted state vectors — the
network was learning from garbage data.
2. GPU path never called monitor.track_reward(), so mean_reward was always
reported as 0.0 in epoch logs despite the agent generating real rewards.
3. Action tracking was double-counted (direct array write + track_action_by_exposure),
inflating diversity metrics by 2x. Consolidated into single bounded call.
Also adds missing app.kubernetes.io/component label to job-template.yaml
so Prometheus training-pods scrape job discovers training pods.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
PSO can now tune sharpe_weight in [0.0, 0.5] instead of hardcoded 0.3.
This lets hyperopt discover the optimal Sharpe ratio blending weight
in the composite reward signal per-symbol.
Also updates docstring to reflect current C1-C4 search space state.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The GPU experience kernel had hardcoded STATE_DIM=54, MARKET_DIM=51,
NUM_ATOMS_MAX=51 but the host-side feature buffer uploads 40 features
per bar and networks use state_dim=56 with up to 100 atoms. Past ~702K
bars the stride mismatch caused out-of-bounds GPU reads → ILLEGAL_ADDRESS.
All dimension constants now use #ifndef guards so the NVRTC JIT compiler
receives the actual values via #define injection — zero runtime overhead.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Hyperopt varies hidden_dim_base (256–1024) but the CUDA experience
kernel hardcoded SHARED_H1=256, SHARED_H2=256. When hyperopt picked
larger dims, the kernel did matvec with wrong strides → illegal memory
access → training crash on first epoch.
Fix: wrap CUDA #defines in #ifndef guards and inject actual dims from
the dueling network config at NVRTC compile time. The kernel is now
specialized per-trial with the exact weight matrix dimensions — zero
runtime overhead, no dimension mismatch possible.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
from_dqn_params() was stripping the last hidden_dim, creating only 1
shared layer (shared_0) when hidden_dims=[256,256]. The CUDA experience
kernel hardcodes 2 shared layers and gpu_weights.rs expects shared_1.*
weight keys. This caused "Missing weight: shared_1.weight" every epoch,
forcing CPU fallback for all experience collection on H100.
Fix: use all hidden_dims as shared layers. Default [256,256] now creates
shared_0 + shared_1, matching the CUDA kernel architecture exactly.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The DQN hyperopt adapter has an explicit trades_data_dir field from CLI
args, but load_ofi_features() was only using the derived sibling path.
Now uses the explicit field when available, falling back to derivation.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The OFI calculator's compute_ofi_from_file() never called feed_trade(),
leaving 3/8 features (VPIN, Kyle's Lambda, trade_imbalance) at zero in
production. Added compute_ofi_with_trades() that interleaves trades by
timestamp into the MBP-10 streaming callback. Updated DQN and PPO
hyperopt adapters to derive trades_dir as sibling of dbn_data_dir.
Smoke test validates: without trades VPIN=0/5000, with trades VPIN=5000/5000.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Tests require a CUDA GPU and are #[ignore]d by default. Run with:
cargo test -p ml --test gpu_kernel_parity_test -- --ignored
Covers:
- Standard dueling forward: finite Q-values, valid action range [0,4]
- C51 distributional forward: Q-values bounded by atom support [-25,25]
- Candle vs kernel Q-value parity: argmax action consistency
- NoisyNet exploration: noise injection produces action diversity
- Weight extraction roundtrip: VarMap → CudaSlice → sync
- Distributional weight shapes: value_out [51,128], advantage_out [255,128]
- RMSNorm gamma extraction: initialized to 1.0
- Repeated kernel launches: 5 consecutive runs all produce finite output
All 8 tests pass on RTX 3050 Ti (4.49s total).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Port factorized Gaussian noise exploration and 51-atom categorical value
distribution to the CUDA experience collection kernel, fixing a correctness
bug where GPU Q-values were wrong when use_distributional=true (production
default) due to misinterpreted distributional weight shapes.
- D5: NoisyNet factorized noise (Box-Muller + f(x)=sign(x)*sqrt(|x|)) on
all 6 dueling layers, online network only — target stays deterministic
- D6: C51 distributional dueling forward with per-action atom softmax,
RMSNorm after shared/value/advantage layers, correct [51,128]/[255,128]
weight interpretation
- RmsNormWeightSet extraction and post-epoch sync (GPU-to-GPU)
- Fix get_effective_epsilon() to report actual 2% noisy floor instead of 0.0
- Proportional diversity entropy penalty (continuous gradient vs cliff)
- 2758 tests passing, 0 failures
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
GPU experience collector was falling back to CPU because it required a
curiosity VarMap, but curiosity_weight=0.0 means the module is never
created. Fix: make curiosity optional (CuriosityWeightSet::zeros() for
GPU buffers, curiosity_scale=0.0 in kernel config). Also require
explicit binary-tag SHA in Argo training workflow (no "latest" fallback).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The walk-forward backtest in the DQN hyperopt adapter constructed batch
tensors with raw state_dim (51/43) but the model expects aligned
state_dim (56/48). This caused shape mismatch errors during backtest
evaluation: matmul [1024, 51] vs [56, 1024].
Fix: use align_dim_for_tensor_cores() and zero-pad each state vector
before tensor construction, matching the same pattern used in
compute_loss_internal.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Additional padding in get_q_values and convert_to_state — these are
currently unused in the training pipeline but would crash if called.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Validation, action selection, and Q-value monitoring paths were using
raw state dimensions (51) while the model expected aligned dims (56).
Training epoch 1 passed because the GPU pipeline pads correctly, but
validation crashed: shape mismatch [1000,51] vs [56,1024].
Fixed: validation batch, select_actions_batch CPU fallback,
estimate_avg_q_value, compute_q_gap — all now zero-pad to aligned dim.
Also fixed model size estimation log to show aligned dims.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add QuestDB ILP sink for training metrics, update Prometheus scrape
configs, and fix network policies for monitoring stack connectivity.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Move BF16 tensor core alignment from per-forward-pass allocation to
data pipeline boundaries. On H100, state_dim 43→48 and 51→56 (8-aligned)
so cuBLAS dispatches HMMA instructions instead of falling back to scalar FMA.
Architecture:
- Trainer computes aligned state_dim at source (align_dim_for_tensor_cores)
- GPU path: DqnGpuData.pad_state_tensor() pads once at upload boundary
- CPU path: train_batch() fold zero-pads Experience.state vectors
- Networks receive pre-aligned tensors — zero per-step overhead
All state_dim defaults updated to aligned values (43→48, 51→56).
Removed pad_to_aligned() from all network forward() methods.
2758 tests pass, 0 failures.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
cuBLAS requires M/N/K dimensions to be multiples of 8 for BF16 tensor
core dispatch. state_dim=51 (with OFI) caused silent fallback to scalar
FMA ops, leaving tensor cores at 0.1% utilization despite BF16 enabled.
Pad state_dim to next 8-multiple (51→56, 43→48) at network construction
and zero-pad input tensors in forward pass across all DQN network types:
Sequential, DuelingQNetwork, DistributionalDuelingQNetwork, NetworkLayers.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Fix NaN detection: replace non-existent isnan() with ne(&self) (NaN≠NaN)
- C51 gradient strip: copy().detach() replaces to_vec2→from_vec GPU→CPU→GPU roundtrip
- GPU batch fast path: skip CPU fold + 5× from_vec when GpuBatch available
- Action validation: GPU clamp() replaces CPU loop in GPU batch path
- PER TD errors: keep as GPU Tensor when GpuPrioritized replay active
- PER indices: use GpuBatch.indices directly instead of CPU Vec→Tensor
- IS weights: cache GPU tensor from GpuBatch, reuse in both loss paths
- Logging: Q-values 10→500 steps, diagnostics 100→1000 steps
2758 tests pass, 0 clippy warnings.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Both adapters now call load_ofi_features_parallel from mbp10_loader
instead of duplicating the rayon + streaming logic inline.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Three fixes:
- Streaming MBP-10 parser (parse_mbp10_streaming): computes OFI inline
during decode — eliminates Vec<Mbp10Snapshot> allocation (41.9M clones)
- Parallel file processing: rayon par_iter across 9 MBP-10 files
(778s sequential → ~90s expected on H100 24-core)
- Fix hardcoded state_dim=54 in walk-forward backtest tensor creation
that caused panic "range end index 55296 out of range for slice of
length 52224" — now uses dynamic state_dim (43 or 51 with OFI)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Root cause: preload_data() called loader.ofi_features.take() on the internal
DQN trainer, but load_training_data() only loads OHLCV bars — it never
populates ofi_features. The OFI loading is done by the hyperopt adapter's
own load_ofi_features() method.
Fixes:
- preload_data() now calls self.load_ofi_features() directly
- load_ofi_features() uses self.mbp10_data_dir when set (was hardcoded ../mbp10)
- input_dim pre-computation uses OFI-aware size (51 when enabled, 43 otherwise)
- CI 'latest' package: delete-then-upload to avoid GitLab duplicate file issue
- Warn when mbp10_data_dir is set but no OFI features loaded
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The hyperopt preload_data() created a loader with default hyperparams
(mbp10_data_dir=None), so MBP-10/trades data was never loaded. Each
trial then set mbp10_data_dir → state_dim=51, but the preloaded data
had no OFI features → shape mismatch [128,43] vs [51,1024].
- Pass mbp10_data_dir/trades_data_dir to preload hyperparams
- Extract ofi_features from loader after preload
- Store as preloaded_ofi_features: Option<Arc<Vec<[f64;8]>>>
- Inject into each trial's DQNTrainer before training
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The GPU path (build_batch_states / build_state_tensor) only concatenated
market[40] + portfolio[3] = 43 dims, while state_dim was set to 51 when
OFI was enabled. This caused shape mismatch [128,43] vs [51,1024].
- Add ofi_features: Option<Tensor> field to DqnGpuData
- Add upload_ofi() method for MBP-10 order book features (8 dims/bar)
- Concatenate OFI in build_batch_states: [count,40]+[count,3]+[count,8]=[count,51]
- Concatenate OFI in build_state_tensor: [1,40]+[1,3]+[1,8]=[1,51]
- Wire trainer to call upload_ofi() after GPU data upload
- Fix CPU path to zero-pad regime_features when OFI enabled but data missing
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add --mbp10-data-dir and --trades-data-dir CLI args to
hyperopt_baseline_rl binary so hyperopt trials can use real
order book and trade data for VPIN/Kyle's Lambda features.
- DQNTrainer: add mbp10_data_dir/trades_data_dir fields + with_ofi_data_dirs() builder
- DQNHyperparameters: pipe through from trainer instead of hardcoded None
- download-trades-job: fix nodeSelector to ci-compile-cpu (platform pool full)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Expand training-data-pvc from 10Gi → 200Gi (OHLCV + MBP-10 + headroom)
- Add data-sync-job: rclone sync from MinIO → PVC (delta-only, fast repeats)
- Add sync-training-data init container to training job template
(auto-syncs data from MinIO before each training run)
- Add training-job + data-sync-job NetworkPolicies (MinIO, Tempo, Pushgateway)
- Add app.kubernetes.io/part-of: foxhunt to training pod template
- download_baseline: add --parallel N flag for concurrent Databento downloads
- download_baseline: delete local files after MinIO upload (saves scratch space)
- Bump download job scratch volume to 100Gi
Architecture: Databento → MinIO (source of truth) → PVC (local cache).
First sync pulls everything; subsequent runs only sync deltas (seconds).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Wire 8 OFI features (OFI L1/L5, depth imbalance, VPIN, Kyle's lambda,
bid/ask slopes, trade imbalance) through the DQN training pipeline:
- Add mbp10_data_dir config field to DQNHyperparameters
- Dynamic state_dim: 43 (no OFI) or 51 (with OFI) based on config
- Compute OFI per bar during data loading, store on trainer
- Pass OFI features through regime_features slot in TradingState
- Configurable MBP-10 path with recursive .dbn/.dbn.zst discovery
- Add zstd auto-detection to DbnParser::parse_mbp10_file()
- Add --mbp10-data-dir CLI flag to train_baseline_rl
- Fix hardcoded [f64; 51] → FeatureVector51 ([f64; 40]) across
examples, walk_forward, GPU memory profile, and test fixtures
- Fix stale state_dim=51 in dqn_config_2025() and DQN tests
2747 tests pass, 0 failures.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- download_baseline now reads schema from universe TOML config
(was hardcoded to ohlcv-1m, now supports mbp-10 and other schemas)
- Add --rclone-dest flag for direct upload to MinIO after each download
- Add config/universe-es-mbp10.toml: ES.FUT MBP-10, same date range
- Add infra/k8s/training/download-mbp10-job.yaml: K8s Job to download
ES.FUT MBP-10 data in-cluster and upload to MinIO
Usage:
kubectl apply -f infra/k8s/training/download-mbp10-job.yaml
Prereqs: databento-credentials secret, download_baseline binary in MinIO
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
batch_greedy_actions, batch_softmax_actions, and
batch_hierarchical_softmax_actions all used self.forward() which routes
through the dist_dueling/dueling/standard Q-network. When use_iqn=true,
the training loss trains the IQN QuantileNetwork but inference never
consulted it — the trained IQN weights were ignored at evaluation time.
Add q_values_for_batch() helper that dispatches to the IQN network
(with CVaR or expected-Q reduction) when use_iqn=true, and wire all
three batch methods through it. select_action, select_action_with_confidence,
and select_action_inference already had correct IQN branches.
Add test_iqn_batch_greedy_actions_uses_iqn_network covering training,
batch greedy, batch softmax, and inference paths with IQN enabled.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add RMSNorm (root mean square normalization) after each hidden layer
in the distributional-dueling Q-network: shared backbone layers, value
stream, and advantage stream. RMSNorm stabilizes activations and
gradients without the overhead of full LayerNorm (no mean centering),
making the network less sensitive to input scale during training.
Architecture per layer: Linear -> LeakyReLU -> RMSNorm
RMSNorm weights are automatically tracked in the existing VarMap since
they are created via VarBuilder::from_varmap with the same shared map.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
1. Walk-forward windows: replaced 3 non-overlapping with sliding (50% overlap, ~5 windows).
Aggregation changed from mean-0.5*std to median-0.5*IQR for outlier robustness.
2. Composite score: tanh normalization prevents Calmar ratio scale dominance
(0.02% drawdowns → values in thousands drowning out Sharpe/Sortino).
3. Q-value overestimation: new Prometheus gauge foxhunt_training_q_overestimation_ratio,
warning log when ratio>10 or q_mean>5, adaptive tau doubles when Q-mean growth>0.5/epoch
(capped at 0.01), decays back when stable.
2742 tests pass, 0 failures.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace stub StalenessTracking trait with real StalenessTracker:
- Per-slot timestamp tracking (last_updated_step per experience)
- get_stale_indices() returns oldest-first for refresh
- Wired into PrioritizedReplayBuffer (mark_updated on priority update)
- Epoch-boundary refresh in DQN trainer: recomputes priorities for
stale entries (>500 steps old) via Q-value forward pass
- 7 staleness tests + 23 PER tests pass, 0 clippy
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- C1: Narrow V_min/V_max from [-15,+15] to [-2,+2] for C51 atom resolution
- C2: Remove exploration stacking (28D→26D), keep NoisyNet only
- C3: Fix entropy regularizer for 5-action space, remove 2x/3x multipliers
- H1: Narrow gamma to [0.88, 0.96] (avoid overnight gap discounting)
- H2: Raise tau lower bound to 0.005 (target net tracks in short trials)
- H3: Cap kelly_fractional at 0.75 (no full-Kelly ruin)
- M1: Enable QR-DQN when num_atoms > 100 (hyperopt-toggled)
- M3: Add Q-value gap logging (Q_best - Q_second_best) per epoch
2735 tests pass, 0 clippy warnings
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The objective function was using buy/sell/hold percentages from training
metrics instead of the backtest. This caused the optimizer to receive stale
action distribution signals that diverged from actual backtest behavior.
Added buy_action_pct/sell_action_pct/hold_action_pct to BacktestMetrics,
counted during the multi-window backtest loop, and used in extract_objective
when backtest metrics are available.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Patience-based early stopping (WAVE 24) was not gated by early_stopping_enabled,
causing ALL hyperopt trials to terminate early and return penalty metrics with
backtest_metrics: None — no backtest ever ran, producing FALLBACK OBJECTIVE 44.6.
Also removes eval_softmax_temp from search space (29D→28D) since backtest uses
greedy argmax, widens gamma range (0.95-0.99→0.90-0.999) for better TPE signal,
and updates all tests to match.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Greedy argmax legitimately converges to 1-2 actions when the model
is confident. The hard gate (unique_actions < 3 → 8.0 penalty) was
blocking ALL trials from using real backtest metrics, forcing FALLBACK.
Changes:
- Remove hard diversity short-circuit gate (unique_actions < 3)
- Reduce soft diversity penalty from 3.0 to 0.8 max (mild TPE signal)
- Fix early_stopping_enabled: false (was self.epochs > 12)
- Update test to validate mono-action policies produce good objectives
Multi-window backtest (3 windows, mean - 0.5*std) already handles
phantom Sharpe from single-bucket flukes.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
