refactor(rl/sac): consolidate hyperparameter ownership and clean up discrete critic

2026-05-16 17:20:05 +00:00 · 2026-04-24 13:18:33 +02:00
parent 06255996ea
commit 1ed32210c7
9 changed files with 162 additions and 190 deletions
@@ -926,7 +926,7 @@ The ideal behaviour is that your intervention rate should drop gradually during

 Some configuration values have a disproportionate impact on training stability and speed:

- **`temperature_init`** (`policy.temperature_init`) – initial entropy temperature in SAC. Higher values encourage more exploration; lower values make the policy more deterministic early on. A good starting point is `1e-2`. We observed that setting it too high can make human interventions ineffective and slow down learning.
+- **`temperature_init`** (`algorithm.temperature_init`) – initial entropy temperature in SAC. Higher values encourage more exploration; lower values make the policy more deterministic early on. A good starting point is `1e-2`. We observed that setting it too high can make human interventions ineffective and slow down learning.
 - **`policy_parameters_push_frequency`** (`policy.actor_learner_config.policy_parameters_push_frequency`) – interval in _seconds_ between two weight pushes from the learner to the actor. The default is `4 s`. Decrease to **1-2 s** to provide fresher weights (at the cost of more network traffic); increase only if your connection is slow, as this will reduce sample efficiency.
 - **`storage_device`** (`policy.storage_device`) – device on which the learner keeps the policy parameters. If you have spare GPU memory, set this to `"cuda"` (instead of the default `"cpu"`). Keeping the weights on-GPU removes CPU→GPU transfer overhead and can significantly increase the number of learner updates per second.