From 44d3ca9db858e68c695d698a66a5f1b5fac3e415 Mon Sep 17 00:00:00 2001
From: MLErik <baerenjesus@gmail.com>
Date: Mon, 24 Jun 2019 10:01:47 -0500
Subject: [PATCH] updated training file
---
torch_training/training_navigation.py | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/torch_training/training_navigation.py b/torch_training/training_navigation.py
index 634db69..de4b792 100644
--- a/torch_training/training_navigation.py
+++ b/torch_training/training_navigation.py
@@ -146,6 +146,9 @@ for trials in range(1, n_trials + 1):
distance = norm_obs_clip(distance)
agent_data = np.clip(agent_data, -1, 1)
obs[a] = np.concatenate((np.concatenate((data, distance)), agent_data))
+ agent_data = env.agents[a]
+ speed = 1 #np.random.randint(1,5)
+ agent_data.speed_data['speed'] = 1. / speed
for i in range(2):
time_obs.append(obs)
@@ -153,6 +156,7 @@ for trials in range(1, n_trials + 1):
for a in range(env.get_num_agents()):
agent_obs[a] = np.concatenate((time_obs[0][a], time_obs[1][a]))
+
score = 0
env_done = 0
# Run episode
@@ -167,7 +171,7 @@ for trials in range(1, n_trials + 1):
if demo:
eps = 0
# action = agent.act(np.array(obs[a]), eps=eps)
- action = 2 #agent.act(agent_obs[a], eps=eps)
+ action = agent.act(agent_obs[a], eps=eps)
action_prob[action] += 1
action_dict.update({a: action})
# Environment step
--
GitLab