foxhunt/config/training/dqn-hyperopt.toml

# DQN Hyperopt Profile — PSO search space definition
# All bounds are [min, max] ranges. The adapter reads these at runtime.
# To constrain the search space, narrow the ranges here — no code changes needed.
#
# Mean-reduced gradients (2026-04-09): LR range shifted down because gradient
# clipping no longer acts as a hidden LR reducer. Old range [1e-5, 3e-4] had
# effective LR of [~5e-10, ~1.5e-8] due to SUM-reduced clipping at batch=16384.

[search_space]
# Base parameters
learning_rate = [1e-7, 1e-4]            # log scale in adapter — mean-reduced gradients
batch_size = [4096, 16384]
gamma = [0.90, 0.99]                    # wider range — v_range computed dynamically from gamma
buffer_size = [50000, 100000]           # log scale in adapter
max_leverage = [2.0, 10.0]             # leverage ratio; position computed from capital/price
huber_delta = [10.0, 40.0]             # log scale in adapter
entropy_coefficient = [0.05, 0.5]
transaction_cost_multiplier = [0.5, 2.0]
per_alpha = [0.4, 0.8]
per_beta_start = [0.2, 0.6]

# Rainbow DQN extensions
v_range = [1.0, 1.0]                   # IGNORED: v_range now computed dynamically from gamma
noisy_sigma_init = [0.1, 1.0]          # log scale in adapter
dueling_hidden_dim = [128, 512]
n_steps = [3, 5]
num_atoms = [52, 100]                   # 51=C51 paper minimum, 101=higher resolution (2x slower but better signal)

# Weight decay
weight_decay = [0.0001, 0.01]          # log scale in adapter

# Kelly risk parameters
kelly_fractional = [0.25, 0.75]
kelly_max_fraction = [0.1, 0.5]

# Volatility
volatility_window = [10, 30]

# Soft update
tau = [0.005, 0.01]                    # log scale in adapter

# Network sizing
hidden_dim_base = [128, 256]           # capped at production default: 512 is 4x slower for marginal benefit

# CQL regularization
cql_alpha = [0.5, 5.0]

# Training dynamics
lr_decay_type = [0, 2]                 # discrete: 0=constant, 1=linear, 2=cosine
dsr_eta = [0.001, 0.05]               # log scale in adapter
minimum_profit_factor = [1.1, 2.0]

# Exploration
count_bonus_coefficient = [0.0, 0.3]

# Risk-adjusted returns
sharpe_weight = [0.0, 0.5]

# Branching DQN
branch_hidden_dim = [64, 256]

# Gradient accumulation
gradient_accumulation_steps = [1, 1]   # fixed at 1 for now

# IQN dual-head
iqn_lambda = [0.0, 2.0]

# Spectral normalization
spectral_norm_sigma_max = [1.0, 10.0]

# C51 warmup
c51_warmup_epochs = [0, 10]
c51_alpha_max = [0.3, 0.9]

# HER ratio
her_ratio = [0.0, 0.8]

# Composite reward weights
w_dsr = [0.1, 2.0]
w_pnl = [0.0, 1.0]
w_dd = [0.0, 5.0]
w_idle = [0.0, 0.1]
dd_threshold = [0.005, 0.03]            # HFT: tight drawdown tolerance (0.5%-3%)
loss_aversion = [1.0, 1.0]
time_decay_rate = [0.0001, 0.005]
position_entropy_weight = [0.01, 0.1]

# Trade conviction filter
q_gap_threshold = [0.0, 0.5]          # 0.0=trade every bar, 0.5=high conviction only

# Reward v7 — Counterfactual Branch Attribution
cea_weight = [0.1, 1.0]
order_credit_weight = [0.0, 0.5]
risk_efficiency_weight = [0.0, 0.5]
urgency_credit_weight = [0.0, 0.5]
exit_timing_weight = [0.0, 0.2]
ofi_reward_weight = [0.0, 0.5]
kelly_sizing_weight = [0.0, 0.5]
reward_noise_scale = [0.01, 0.1]
# exposure_aux_weight removed (4-branch refactor)
b3_size = 3

# v8 search ranges
micro_reward_scale = [0.0, 0.05]
td_lambda = [0.5, 0.99]
hindsight_fraction = [0.0, 0.3]
hindsight_lookahead = [5, 20]
epsilon_start = [0.1, 0.5]
epsilon_end = [0.01, 0.05]

[experience]
initial_capital = 100000.0

[experience.fill_simulation]
ioc_fill_prob = 0.85
limit_fill_min = 0.30
limit_fill_max = 0.80
tx_cost_multiplier = 0.18  # IBKR ES: 0.18 bps = $4.50/contract RT
min_hold_bars = 10  # ~26s hold at 23 volume bars/min
spread_cost_frac = 0.50
spread_capture_frac = 0.50

[risk]
q_clip_min = -200.0
q_clip_max = 200.0

[reward]
# v8 comprehensive training overhaul
micro_reward_scale = 0.01
td_lambda = 0.9
max_trace_length = 7
hindsight_fraction = 0.1
hindsight_lookahead = 10
w_dsr = 1.0
w_pnl = 0.3
w_dd = 1.0
w_idle = 0.01
dd_threshold = 0.01
loss_aversion = 1.0
time_decay_rate = 0.0005
q_gap_threshold = 0.1
cea_weight = 0.3
order_credit_weight = 0.1
risk_efficiency_weight = 0.1
urgency_credit_weight = 0.1
exit_timing_weight = 0.05
ofi_reward_weight = 0.2
kelly_sizing_weight = 0.1
reward_noise_scale = 0.05
b3_size = 3

[fixed]

[pso]
swarm_size = 20
max_iterations = 50
inertia = 0.7
cognitive = 1.5
social = 1.5

# Two-phase hyperopt: Phase 1 fixes architecture to small network,
# searches only learning dynamics (~15D). Phase 2 fixes best dynamics
# from Phase 1 JSON, searches architecture (~5D).
# See: docs/superpowers/specs/2026-03-22-two-phase-hyperopt-design.md
[phase_fast]
hidden_dim_base = 128
num_atoms = 101
branch_hidden_dim = 64
dueling_hidden_dim = 128
v_range = 1.0
# v8 phase_fast overrides
micro_reward_scale = 0.01
td_lambda = 0.9
hindsight_fraction = 0.1
hindsight_lookahead = 10
w_dsr = 1.0
w_pnl = 0.3
w_dd = 1.0
w_idle = 0.01
dd_threshold = 0.01
loss_aversion = 1.0
time_decay_rate = 0.0005
q_gap_threshold = 0.1
cea_weight = 0.3
order_credit_weight = 0.1
risk_efficiency_weight = 0.1
urgency_credit_weight = 0.1
exit_timing_weight = 0.05
ofi_reward_weight = 0.2
kelly_sizing_weight = 0.1
reward_noise_scale = 0.05
b3_size = 3