AI4Finance-Foundation / AI4Finance-Foundation/FinRL
DDPG / off-policy algorithms fail due to rollout_buffer logging in FinRL 0.3.8
Open
- Dominant language
- Jupyter Notebook
- Stars
- 16.3k
- Forks
- 3.5k
- PR merge metrics
- No merged PRs in 30d
Description
I encountered a logging error when training off-policy algorithms (DDPG, TD3, SAC) in FinRL 0.3.8.
Root cause:
FinRL logging assumes the presence of `rollout_buffer`, which only exists for on-policy algorithms (A2C, PPO). Off-policy algorithms use `replay_buffer`, so the callback raises a logging error during training.
This does not break training itself, but breaks logging / TensorBoard
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.