Model Training

SlinkyLayer turns raw exchange data into a deployable trading policy through a repeatable, five–step workflow. Each run is archived as a JSON spec plus content hashes, so any compliant node can reproduce the result exactly.

---

Wizard Overview

Step	Required fields	Notes
1) Market	exchange, symbol, timeframe	Three bar sizes (5 m, 15 m, 60 m).
2) Split	train_start, test_start	Presets: Short, Medium, Long; Custom allowed.
3) Reward	reward_name, params	Default return_minus_cost; alternatives Sharpe-scaled, log-return, trade-count, win-loss.
4) Budget	total_timesteps, n_envs	Auto = 10 × bars-in-train, clamped 2e5–2e6; presets Quick / Standard / Thorough.
5) Hyper-params	algo, net_arch, lr, n_steps …	Hidden in Beginner mode; fully editable in Professional mode.

Client-side checks enforce safe ranges, e.g. for PPO (n_steps×n_envs) mod  batch_size =0

---

Supported Algorithms

Algo	Style	Memory	Typical use
PPO	on-policy	rollout only	General workhorse; stable on parallel workers.
A2C	on-policy	rollout only	Minimal compute; rapid feedback.
SAC	off-policy	replay buffer	Sample-efficient; handles noisy returns.
TD3	off-policy	replay buffer	Deterministic, twin critics, action noise.
DDPG	off-policy	replay buffer	Legacy deterministic baseline.

All share an MLP policy; layer sizes (net_arch) and activation (Tanh or ReLU) are user-selectable.

---

Training Pipeline

rollout_pods  →  learner_GPU  →  checkpoint
      ↑               |               |
feature_table   metrics stream   back-test job

1. Rollout pods run n_envs vectorised environments, each stepping n_steps with the chosen fee, slippage, and short settings.

2. Learner pod computes gradients on GPU, applies Adam updates, and checkpoints every k updates.

3. Back-test job replays the frozen policy on the unseen test split; outputs equity curve, Sharpe, Sortino, max drawdown.

---

Reproducibility and Forward Audit

Artefacts stored per run

File	Purpose
config.json	Full wizard output.
data_hash.txt	SHA-256 of training candles.
feature_hash.txt	CID of indicator table.
checkpoint.pt	Final weights.
metrics.json	Risk metrics on test split.

Audit path

Auditor nodes subscribe to the live signal stream only.

1. Verify arrival ≤ 5 s after candle close.

2. Recompute one-step reward using canonical price feed.

3. Sign segment hash; quorum of three identical receipts marks the segment verified on chain.

Auditors never receive private hyper-parameter sweeps, keeping intellectual property safe while giving traders cryptographic proof that signals are fresh and honest.