gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2025-12-17 19:20:19 +01:00
Code Issues Projects Releases Wiki Activity

integration test changes to reach the train part (#254)

Browse Source 
* integration test changes to override heatup to 1000 steps +  run each preset for 30 sec (to make sure we reach the train part)

* fixes to failing presets uncovered with this change + changes in the golden testing to properly test BatchRL

* fix for rainbow dqn

* fix to gym_environment (due to a change in Gym 0.12.1) + fix for rainbow DQN + some bug-fix in utils.squeeze_list

* fix for NEC agent
This commit is contained in:
Gal Leibovich
2019-03-27 21:14:19 +02:00
committed by GitHub
parent 6e08c55ad5
commit 310d31c227
8 changed files with 28 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
rl_coach/agents/agent.py
View File

@@ -398,7 +398,10 @@ class Agent(AgentInterface):
self.accumulated_shaped_rewards_across_evaluation_episodes = 0
self.num_successes_across_evaluation_episodes = 0
self.num_evaluation_episodes_completed = 0
if self.ap.is_a_highest_level_agent or self.ap.task_parameters.verbosity == "high":
# TODO verbosity was mistakenly removed from task_parameters on release 0.11.0, need to bring it back
# if self.ap.is_a_highest_level_agent or self.ap.task_parameters.verbosity == "high":
if self.ap.is_a_highest_level_agent:
screen.log_title("{}: Starting evaluation phase".format(self.name))
elif ending_evaluation:
@@ -416,7 +419,10 @@ class Agent(AgentInterface):
self.agent_logger.create_signal_value(
"Success Rate",
success_rate)
if self.ap.is_a_highest_level_agent or self.ap.task_parameters.verbosity == "high":
# TODO verbosity was mistakenly removed from task_parameters on release 0.11.0, need to bring it back
# if self.ap.is_a_highest_level_agent or self.ap.task_parameters.verbosity == "high":
if self.ap.is_a_highest_level_agent:
screen.log_title("{}: Finished evaluation phase. Success rate = {}, Avg Total Reward = {}"
.format(self.name, np.round(success_rate, 2), np.round(evaluation_reward, 2)))
@@ -565,7 +571,9 @@ class Agent(AgentInterface):
self.parent_level_manager.parent_graph_manager.time_metric == TimeTypes.EpisodeNumber:
self.update_log()
if self.ap.is_a_highest_level_agent or self.ap.task_parameters.verbosity == "high":
# TODO verbosity was mistakenly removed from task_parameters on release 0.11.0, need to bring it back
# if self.ap.is_a_highest_level_agent or self.ap.task_parameters.verbosity == "high":
if self.ap.is_a_highest_level_agent:
self.log_to_screen()
def reset_internal_state(self) -> None: