oxbrbtx/PrimAITE
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

#917 - Overhauled transaction and mean reward writing.

Browse Source 
- Separated out learning outputs from evaluation outputs
This commit is contained in:
Chris McCarthy
2023-06-28 16:34:00 +01:00
parent 7482192046
commit 1d3778f400
13 changed files with 258 additions and 250 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/primaite/config/_package_data/training/training_config_main.yaml
View File

@@ -38,7 +38,7 @@ hard_coded_agent_view: FULL
action_type: ANY
# Number of episodes to run per session
num_episodes: 10
num_episodes: 1000
# Number of time_steps per episode
num_steps: 256