gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2025-12-17 11:10:20 +01:00
Code Issues Projects Releases Wiki Activity

Enabling-more-agents-for-Batch-RL-and-cleanup (#258)

Browse Source 
allowing for the last training batch drawn to be smaller than batch_size + adding support for more agents in BatchRL by adding softmax with temperature to the corresponding heads + adding a CartPole_QR_DQN preset with a golden test + cleanups
This commit is contained in:
Gal Leibovich
2019-03-21 16:10:29 +02:00
committed by GitHub
parent abec59f367
commit 6e08c55ad5
24 changed files with 152 additions and 69 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
rl_coach/agents/clipped_ppo_agent.py
View File

@@ -207,6 +207,8 @@ class ClippedPPOAgent(ActorCriticAgent):
self.networks['main'].online_network.output_heads[1].likelihood_ratio,
self.networks['main'].online_network.output_heads[1].clipped_likelihood_ratio]
# TODO-fixme if batch.size / self.ap.network_wrappers['main'].batch_size is not an integer, we do not train on
# some of the data
for i in range(int(batch.size / self.ap.network_wrappers['main'].batch_size)):
start = i * self.ap.network_wrappers['main'].batch_size
end = (i + 1) * self.ap.network_wrappers['main'].batch_size