Skip to content

Add DDPG training script - #21

Merged
Jordan-Leis merged 2 commits into
mainfrom
a5/ddpg
Feb 6, 2026
Merged

Add DDPG training script#21
Jordan-Leis merged 2 commits into
mainfrom
a5/ddpg

Conversation

@ammiellewb

Copy link
Copy Markdown
Collaborator
  • Implement DDPG (Deep Deterministic Policy Gradient) algorithm
  • Support both Normal and Ornstein-Uhlenbeck action noise
  • Include DDPG-specific hyperparameters (tau, learning_rate, buffer_size, etc.)
  • Integrate with existing metrics logging and W&B support
  • Follow same pattern as SAC training script

ammiellewb and others added 2 commits February 2, 2026 21:26
- Implement DDPG (Deep Deterministic Policy Gradient) algorithm
- Support both Normal and Ornstein-Uhlenbeck action noise
- Include DDPG-specific hyperparameters (tau, learning_rate, buffer_size, etc.)
- Integrate with existing metrics logging and W&B support
- Follow same pattern as SAC training script
Add `venv/` to `.gitignore` to prevent committing local virtual envs,
and include `rainflow` in `requirements.txt` for rainflow cycle counting support.

@Jordan-Leis Jordan-Leis left a comment

Copy link
Copy Markdown
Owner

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Looks like a clean implementation

@Jordan-Leis
Jordan-Leis merged commit 4ddd7f4 into main Feb 6, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants