pytorch/examples

Actor critic example not using discount rate properly

Open

#744 opened on Mar 27, 2020

View on GitHub
 (3 comments) (0 reactions) (0 assignees)Python (9,429 forks)batch import
good first issuetriaged

Repository metrics

Stars
 (21,634 stars)
PR merge metrics
 (No merged PRs in 30d)

Description

The Actor Critic example (which is actually an implementation of REINFORCE-with-baseline as pointed out in https://github.com/pytorch/examples/issues/573), does not use the discount rate properly.

The loss should include \gamma ^ t, as shown in the box on page 330 of Sutton & Barto:

image

Contributor guide

Research direction
Inspect the actor critic example code, locate the loss computation, and modify it to include the discount factor (gamma^t) as per the REINFORCE with baseline algorithm from Sutton & Barto.
Tech stack
pythonpytorch
Domain
machine learningai
Issue type
Bug
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
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
PythonPyTorchGit
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
65