DLR-RM/stable-baselines3

[Feature Request] independently configurable learning rates for actor and critic

Open

#338 opened on Mar 3, 2021

View on GitHub
 (11 comments) (1 reaction) (0 assignees)Python (1,407 forks)batch import
enhancementhelp wanted

Repository metrics

Stars
 (6,550 stars)
PR merge metrics
 (Avg merge 11d 13h) (3 merged PRs in 30d)

Description

🚀 Feature

independently configurable learning rates for actor and critic in AC-style algorithms

Motivation

In literature the actor is often configured to learn slower, such that the critics responses are more reliable. At least it would be nice if i could allow my hyperparameter optimizer to decide which learning rates he wants to use for actor or critic.

Pitch

https://github.com/DLR-RM/stable-baselines3/blob/65100a4b040201035487363a396b84ea721eb027/stable_baselines3/ddpg/ddpg.py#L12-L26

Additional context

https://spinningup.openai.com/en/latest/algorithms/ddpg.html#documentation-pytorch-version

Contributor guide

Research direction
Modify the DDPG class to accept separate learning rates for actor and critic, following the pattern of existing parameters. See the linked code section and the spinningup documentation for reference.
Tech stack
pythonpytorch
Domain
machine learningai
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
2
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Half day
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
PythonGitPyTorch
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
75