Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
N
neurips2020-flatland-starter-kit
Manage
Activity
Members
Code
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Deploy
Releases
Model registry
Analyze
Contributor analytics
Repository analytics
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
adrian_egli
neurips2020-flatland-starter-kit
Commits
6155bff8
Commit
6155bff8
authored
4 years ago
by
Egli Adrian (IT-SCI-API-PFI)
Browse files
Options
Downloads
Patches
Plain Diff
eps disabled
parent
d4efd784
No related branches found
No related tags found
No related merge requests found
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
reinforcement_learning/multi_agent_training.py
+1
-1
1 addition, 1 deletion
reinforcement_learning/multi_agent_training.py
with
1 addition
and
1 deletion
reinforcement_learning/multi_agent_training.py
+
1
−
1
View file @
6155bff8
...
...
@@ -181,7 +181,7 @@ def train_agent(train_params, train_env_params, eval_env_params, obs_params):
elif
train_params
.
policy
==
"
PPO
"
:
policy
=
PPOPolicy
(
state_size
,
get_action_size
(),
use_replay_buffer
=
False
,
in_parameters
=
train_params
)
elif
train_params
.
policy
==
"
DeadLockAvoidance
"
:
policy
=
DeadLockAvoidanceAgent
(
train_env
,
get_action_size
())
policy
=
DeadLockAvoidanceAgent
(
train_env
,
get_action_size
()
,
enable_eps
=
False
)
elif
train_params
.
policy
==
"
DeadLockAvoidanceWithDecision
"
:
# inter_policy = PPOPolicy(state_size, get_action_size(), use_replay_buffer=False, in_parameters=train_params)
inter_policy
=
DDDQNPolicy
(
state_size
,
get_action_size
(),
train_params
)
...
...
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment