oxbrbtx/PrimAITE
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

#1566 - Refactored the test_train_eval_episode_steps.py to sue TempPrimaiteSession.

Browse Source 
- Fixed all errors that were caused b fixing the above.
- Some tests still fail, these are for SS to fix.
- Dropped the old run_generic stuff from conftest.py
This commit is contained in:
Chris McCarthy
2023-07-07 15:50:14 +01:00
parent d49f73f139
commit 40381833d3
15 changed files with 69 additions and 279 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
src/primaite/agents/agent.py
View File

@@ -153,12 +153,11 @@ class AgentSessionABC(ABC):
metadata_dict = json.load(file)
metadata_dict["end_datetime"] = datetime.now().isoformat()
if not self.is_eval:
metadata_dict["learning"]["total_episodes"] = self._env.episode_count # noqa
metadata_dict["learning"]["total_episodes"] = self._env.actual_episode_count # noqa
metadata_dict["learning"]["total_time_steps"] = self._env.total_step_count # noqa
else:
metadata_dict["evaluation"]["total_episodes"] = self._env.episode_count # noqa
metadata_dict["evaluation"]["total_episodes"] = self._env.actual_episode_count # noqa
metadata_dict["evaluation"]["total_time_steps"] = self._env.total_step_count # noqa
filepath = self.session_path / "session_metadata.json"
@@ -209,10 +208,11 @@ class AgentSessionABC(ABC):
:param kwargs: Any agent-specific key-word args to be passed.
"""
self._env.set_as_eval() # noqa
self.is_eval = True
self._plot_av_reward_per_episode(learning_session=False)
_LOGGER.info("Finished evaluation")
if self._can_evaluate:
self._plot_av_reward_per_episode(learning_session=False)
self._update_session_metadata_file()
self.is_eval = True
_LOGGER.info("Finished evaluation")
@abstractmethod
def _get_latest_checkpoint(self):

9
src/primaite/agents/rllib.py
View File

@@ -85,8 +85,12 @@ class RLlibAgent(AgentSessionABC):
metadata_dict = json.load(file)
metadata_dict["end_datetime"] = datetime.now().isoformat()
metadata_dict["total_episodes"] = self._current_result["episodes_total"]
metadata_dict["total_time_steps"] = self._current_result["timesteps_total"]
if not self.is_eval:
metadata_dict["learning"]["total_episodes"] = self._current_result["episodes_total"] # noqa
metadata_dict["learning"]["total_time_steps"] = self._current_result["timesteps_total"] # noqa
else:
metadata_dict["evaluation"]["total_episodes"] = self._current_result["episodes_total"] # noqa
metadata_dict["evaluation"]["total_time_steps"] = self._current_result["timesteps_total"] # noqa
filepath = self.session_path / "session_metadata.json"
_LOGGER.debug(f"Updating Session Metadata file: {filepath}")
@@ -150,7 +154,6 @@ class RLlibAgent(AgentSessionABC):
super().learn()
def evaluate(
self,
**kwargs,

6
src/primaite/agents/sb3.py
View File

@@ -58,7 +58,7 @@ class SB3Agent(AgentSessionABC):
PPOMlp,
self._env,
verbose=self.sb3_output_verbose_level,
n_steps=self._training_config.num_eval_steps,
n_steps=self._training_config.num_train_steps,
tensorboard_log=str(self._tensorboard_log_path),
seed=self._training_config.seed,
)
@@ -93,7 +93,7 @@ class SB3Agent(AgentSessionABC):
for i in range(episodes):
self._agent.learn(total_timesteps=time_steps)
self._save_checkpoint()
self._env.reset()
self._env._write_av_reward_per_episode() # noqa
self.save()
self._env.close()
super().learn()
@@ -129,7 +129,7 @@ class SB3Agent(AgentSessionABC):
if isinstance(action, np.ndarray):
action = np.int64(action)
obs, rewards, done, info = self._env.step(action)
self._env.reset()
self._env._write_av_reward_per_episode() # noqa
self._env.close()
super().evaluate()