search

polixir / OfflineRL

A collection of offline reinforcement learning algorithms.
Apache License 2.0
149 stars 20 forks source link

Cumulative rewards drop sharply #14

Open greenantoflw opened 2 months ago

greenantoflw commented 2 months ago

When i run mopo , i find that the Cumulative rewards drop sharply. Why? Has this ever happened to you too? Thanks 1714379756906

image

SongyiGao commented 1 month ago

Can you provide a record chart of other indicators during training to help locate the problem?