pytorch / pytorch/rl

[Feature Request] `MultiDiscreteTensorSpec` in DQN

Open
#1,077 6 comments 0 reactions 1 assignee View on GitHub

@vmoens is already working on this.

Since Apr 22, 2023.

enhancement
Dominant language
Python
Stars
3.6k
Forks
487
Avg merge
1d 1h
Merged PRs (30d)
207

Description

Currently, DQN modules and losses want to know

 action_space (str, optional): The action space to be considered.
            Must be one of
            ``"one-hot"``, ``"mult_one_hot"``, ``"binary"`` or ``"categorical"``.

We need to add multi categorical to this (MultiDiscreteTensorSpec) and make it work in the modules and losses.

EDIT: following paragraph was solved

Plus, would it be possible to drop this argument and infer it from the action spec?
It seems redundant to me that I need to feed my DQN loss both the spec and a string which repeats a part of the spec

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.