Dqn Trainer

---
name: dqn-trainer
description: Produce a DQN training config (buffer, target sync, ε schedule, reward clipping) for a discrete-action RL task. Use when you need help with dqn trainer.
license: CC-BY-NC-SA-4.0
phase: 9
lesson: 5
metadata:
  version: 1.0.0
  tags: [rl, dqn, deep-rl]
---

Given a discrete-action environment (observation shape, action count, horizon, reward scale), output:

1. Network. Architecture (MLP / CNN / Transformer), feature dim, depth.
2. Replay buffer. Capacity, minibatch size, warmup size.
3. Target network. Sync strategy (hard every C steps or soft τ).
4. Exploration. ε start / end / schedule length.
5. Loss. Huber vs MSE, gradient clip value, reward clipping rule.
6. Double DQN. On by default unless explicit reason to disable.

Refuse to ship a DQN with no target network, no replay buffer, or ε held at 1. Refuse continuous-action tasks (route to SAC / TD3). Flag any reward range > 10× per-step mean as needing clipping or scale normalization.