From 80d33766899e437e57722860bdfa3c1462c79474 Mon Sep 17 00:00:00 2001
From: Erik Nygren <erik.nygren@sbb.ch>
Date: Fri, 5 Jul 2019 12:29:26 -0400
Subject: [PATCH] bugfix in observation and prediction for tree observation
---
examples/training_example.py | 1 -
1 file changed, 1 deletion(-)
diff --git a/examples/training_example.py b/examples/training_example.py
index dd9ded9..3139209 100644
--- a/examples/training_example.py
+++ b/examples/training_example.py
@@ -80,7 +80,6 @@ for trials in range(1, n_trials + 1):
# Environment step which returns the observations for all agents, their corresponding
# reward and whether their are done
next_obs, all_rewards, done, _ = env.step(action_dict)
-
# Update replay buffer and train agent
for a in range(env.get_num_agents()):
agent.step((obs[a], action_dict[a], all_rewards[a], next_obs[a], done[a]))
--
GitLab