gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2025-12-17 19:20:19 +01:00
Code Issues Projects Releases Wiki Activity

Simulating the act on the trainer. (#65)

Browse Source 
* Remove the use of daemon threads for Redis subscribe.
* Emulate act and observe on trainer side to update internal vars.
This commit is contained in:
Ajay Deshpande
2018-11-15 08:38:58 -08:00
committed by Balaji Subramaniam
parent fe6857eabd
commit fde73ced13
13 changed files with 221 additions and 55 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
rl_coach/training_worker.py
View File

@@ -31,7 +31,14 @@ def training_worker(graph_manager, checkpoint_dir):
# evaluation offset
eval_offset = 1
graph_manager.setup_memory_backend()
while(steps < graph_manager.improve_steps.num_steps):
graph_manager.phase = core_types.RunPhase.TRAIN
graph_manager.fetch_from_worker(num_steps=graph_manager.agent_params.algorithm.num_consecutive_playing_steps.num_steps)
graph_manager.phase = core_types.RunPhase.UNDEFINED
if graph_manager.should_train():
steps += 1