thu-ml/tianshou

Need a flexible method to record training data in TensorBoard

Open

#895 opened on Jun 29, 2023

View on GitHub
 (5 comments) (0 reactions) (1 assignee)Python (1,072 forks)batch import
enhancementgood first issue

Repository metrics

Stars
 (7,121 stars)
PR merge metrics
 (No merged PRs in 30d)

Description

  • I have marked all applicable categories:
    • exception-raising bug
    • RL algorithm bug
    • documentation request (i.e. "X is missing from the documentation.")
    • new feature request
  • I have visited the source website
  • I have searched through the issue tracker for duplicates
  • I have mentioned version numbers, operating system and environment, where applicable: 
    import tianshou, gymnasium as gym, torch, numpy, sys
print(tianshou.__version__, gym.__version__, torch.__version__, numpy.__version__, sys.version, sys.platform)
0.5.0 0.26.3 1.12.1 1.21.5 3.7.13 (default, Oct 18 2022, 18:57:03) 
[GCC 11.2.0] linux

Hello, Thanks for your brilliant work! While working with Tianshou, I encountered an issue related to recording training data in TensorBoard. Specifically, I need to record a value from the info dictionary, let's say info["key"], which is similar to an accumulated reward at the end of each episode.

Contributor guide

Research direction
Implement a wrapper or hook to allow logging arbitrary info dictionary keys from the environment or policy into TensorBoard.
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.
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
PythonPyTorch
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
75