Skip to content
Snippets Groups Projects
Commit f77cddf3 authored by Egli Adrian (IT-SCI-API-PFI)'s avatar Egli Adrian (IT-SCI-API-PFI)
Browse files

Policy updated

parent e28c57e5
No related branches found
No related tags found
No related merge requests found
Hide whitespace changes
Inline Side-by-side
reinforcement_learning/multi_agent_training.py
+ 2
− 2
View file @ f77cddf3
...@@ -173,11 +173,11 @@ def train_agent(train_params, train_env_params, eval_env_params, obs_params): ...@@ -173,11 +173,11 @@ def train_agent(train_params, train_env_params, eval_env_params, obs_params):
policy = None policy = None
if False: if False:
policy = DDDQNPolicy(state_size, get_action_size(), train_params) policy = DDDQNPolicy(state_size, get_action_size(), train_params)
if False: if True:
policy = PPOPolicy(state_size, get_action_size(), use_replay_buffer=False, in_parameters=train_params) policy = PPOPolicy(state_size, get_action_size(), use_replay_buffer=False, in_parameters=train_params)
if False: if False:
policy = DeadLockAvoidanceAgent(train_env, get_action_size()) policy = DeadLockAvoidanceAgent(train_env, get_action_size())
if True: if False:
# inter_policy = PPOPolicy(state_size, get_action_size(), use_replay_buffer=False, in_parameters=train_params) # 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) inter_policy = DDDQNPolicy(state_size, get_action_size(), train_params)
policy = DeadLockAvoidanceWithDecisionAgent(train_env, state_size, get_action_size(), inter_policy) policy = DeadLockAvoidanceWithDecisionAgent(train_env, state_size, get_action_size(), inter_policy)
......
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment