From 52d6b38b5ae55a9f583dc6dec6bbddcbf75d0bd8 Mon Sep 17 00:00:00 2001
From: "Egli Adrian (IT-SCI-API-PFI)" <adrian.egli@sbb.ch>
Date: Tue, 3 Nov 2020 21:14:12 +0100
Subject: [PATCH] DeadLockAvoidanceAgent -> observation
---
reinforcement_learning/multi_agent_training.py | 2 +-
run.py | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/reinforcement_learning/multi_agent_training.py b/reinforcement_learning/multi_agent_training.py
index fd85fdc..04c32db 100755
--- a/reinforcement_learning/multi_agent_training.py
+++ b/reinforcement_learning/multi_agent_training.py
@@ -475,7 +475,7 @@ def eval_policy(env, tree_observation, policy, train_params, obs_params):
if __name__ == "__main__":
parser = ArgumentParser()
parser.add_argument("-n", "--n_episodes", help="number of episodes to run", default=2500, type=int)
- parser.add_argument("-t", "--training_env_config", help="training config id (eg 0 for Test_0)", default=0, type=int)
+ parser.add_argument("-t", "--training_env_config", help="training config id (eg 0 for Test_0)", default=2, type=int)
parser.add_argument("-e", "--evaluation_env_config", help="evaluation config id (eg 0 for Test_0)", default=0,
type=int)
parser.add_argument("--n_evaluation_episodes", help="number of evaluation episodes", default=5, type=int)
diff --git a/run.py b/run.py
index 637bc79..fb16e53 100644
--- a/run.py
+++ b/run.py
@@ -25,7 +25,7 @@ from reinforcement_learning.dddqn_policy import DDDQNPolicy
VERBOSE = True
# Checkpoint to use (remember to push it!)
-checkpoint = "./checkpoints/201103172118-0.pth"
+checkpoint = "./checkpoints/201103180606-1400.pth"
# Use last action cache
USE_ACTION_CACHE = True
--
GitLab