af940671bc
Add 7 composite reward fields to DQNHyperparameters: w_dsr, w_pnl, w_dd, w_idle, dd_threshold, loss_aversion, time_decay_rate. Add RewardSection to training_profile.rs with Option<f64> fields and apply_to() mapping. Add [reward] section to all 3 DQN TOML profiles (production, smoketest, hyperopt) with identical defaults. Remove hold_reward from ExperienceSection (replaced by w_idle). Add 7 reward search bounds to SearchSpaceSection and bound() match. Add 7 reward phase_fast defaults to PhaseFastSection. hold_penalty kept as deprecated field for hyperopt adapter compat (Task 4 will clean it up). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
112 lines
2.9 KiB
TOML
112 lines
2.9 KiB
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.
|
|
|
|
[search_space]
|
|
# Base parameters
|
|
learning_rate = [0.00001, 0.0003] # log scale in adapter
|
|
batch_size = [64, 512]
|
|
gamma = [0.88, 0.99]
|
|
buffer_size = [50000, 100000] # log scale in adapter
|
|
max_position_absolute = [1.0, 4.0]
|
|
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 = [10.0, 50.0] # symmetric: v_min=-v_range, v_max=+v_range
|
|
noisy_sigma_init = [0.1, 1.0] # log scale in adapter
|
|
dueling_hidden_dim = [128, 512]
|
|
n_steps = [3, 5]
|
|
num_atoms = [11, 51] # 11=RTX3050, 51=H100 default (101 is 2x slower for marginal benefit)
|
|
|
|
# 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 = [0.0, 1.0]
|
|
|
|
# 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]
|
|
|
|
# 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 = [0.01, 0.10]
|
|
loss_aversion = [1.0, 3.0]
|
|
time_decay_rate = [0.0001, 0.005]
|
|
|
|
[reward]
|
|
w_dsr = 1.0
|
|
w_pnl = 0.3
|
|
w_dd = 1.0
|
|
w_idle = 0.01
|
|
dd_threshold = 0.02
|
|
loss_aversion = 1.5
|
|
time_decay_rate = 0.0005
|
|
|
|
[fixed]
|
|
use_branching = true # GPU pipeline requires branching
|
|
use_double_dqn = true
|
|
use_per = true
|
|
use_distributional = true
|
|
|
|
[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 = 11
|
|
branch_hidden_dim = 64
|
|
dueling_hidden_dim = 128
|
|
v_range = 20.0
|
|
w_dsr = 1.0
|
|
w_pnl = 0.3
|
|
w_dd = 1.0
|
|
w_idle = 0.01
|
|
dd_threshold = 0.02
|
|
loss_aversion = 1.5
|
|
time_decay_rate = 0.0005
|