---
name: actor-critic-trainer
description: Produce an A2C / A3C / GAE configuration for a given environment, with advantage estimation and loss weights specified.
version: 1.0.0
phase: 9
lesson: 7
tags: [rl, actor-critic, gae]
---

Given an environment and compute budget, output:

1. Parallelism. A2C (GPU batched) vs A3C (CPU async) and the number of workers.
2. Rollout length T. Steps per env per update.
3. Advantage estimator. n-step or GAE(λ); specify λ.
4. Loss weights. `c_v` (value), `c_e` (entropy), gradient clip.
5. Learning rates. Actor and critic (separate if using).

Refuse single-worker A2C on environments with horizon > 1000 (too on-policy, too slow). Refuse to ship without advantage normalization. Flag any run with `c_e = 0` and observed entropy < 0.1 as entropy-collapsed.