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

1566 - added test file and edited configs to include types of num steps and modifed agents to use correct step and episode counts

Browse Source
This commit is contained in:
SunilSamra
2023-07-07 14:13:47 +01:00
parent 3ff081ea71
commit 79d98e977b
20 changed files with 652 additions and 60 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/primaite/agents/agent.py
View File

@@ -348,8 +348,8 @@ class HardCodedAgentSessionABC(AgentSessionABC):
self._env.set_as_eval() # noqa
self.is_eval = True
time_steps = self._training_config.num_steps
episodes = self._training_config.num_episodes
time_steps = self._training_config.num_eval_steps
episodes = self._training_config.num_eval_episodes
obs = self._env.reset()
for episode in range(episodes):

10
src/primaite/agents/rllib.py
View File

@@ -107,13 +107,13 @@ class RLlibAgent(AgentSessionABC):
),
)
self._agent_config.training(train_batch_size=self._training_config.num_steps)
self._agent_config.training(train_batch_size=self._training_config.num_train_steps)
self._agent_config.framework(framework="tf")
self._agent_config.rollouts(
num_rollout_workers=1,
num_envs_per_worker=1,
horizon=self._training_config.num_steps,
horizon=self._training_config.num_train_steps,
)
self._agent: Algorithm = self._agent_config.build(logger_creator=_custom_log_creator(self.learning_path))
@@ -121,7 +121,7 @@ class RLlibAgent(AgentSessionABC):
checkpoint_n = self._training_config.checkpoint_every_n_episodes
episode_count = self._current_result["episodes_total"]
if checkpoint_n > 0 and episode_count > 0:
if (episode_count % checkpoint_n == 0) or (episode_count == self._training_config.num_episodes):
if (episode_count % checkpoint_n == 0) or (episode_count == self._training_config.num_train_episodes):
self._agent.save(str(self.checkpoints_path))
def learn(
@@ -133,8 +133,8 @@ class RLlibAgent(AgentSessionABC):
:param kwargs: Any agent-specific key-word args to be passed.
"""
time_steps = self._training_config.num_steps
episodes = self._training_config.num_episodes
time_steps = self._training_config.num_train_steps
episodes = self._training_config.num_train_episodes
_LOGGER.info(f"Beginning learning for {episodes} episodes @" f" {time_steps} time steps...")
for i in range(episodes):

11
src/primaite/agents/sb3.py
View File

@@ -53,11 +53,12 @@ class SB3Agent(AgentSessionABC):
session_path=self.session_path,
timestamp_str=self.timestamp_str,
)
self._agent = self._agent_class(
PPOMlp,
self._env,
verbose=self.sb3_output_verbose_level,
n_steps=self._training_config.num_steps,
n_steps=self._training_config.num_eval_steps,
tensorboard_log=str(self._tensorboard_log_path),
)
@@ -82,8 +83,8 @@ class SB3Agent(AgentSessionABC):
:param kwargs: Any agent-specific key-word args to be passed.
"""
time_steps = self._training_config.num_steps
episodes = self._training_config.num_episodes
time_steps = self._training_config.num_train_steps
episodes = self._training_config.num_train_episodes
self.is_eval = False
_LOGGER.info(f"Beginning learning for {episodes} episodes @" f" {time_steps} time steps...")
for i in range(episodes):
@@ -104,8 +105,8 @@ class SB3Agent(AgentSessionABC):
:param deterministic: Whether the evaluation is deterministic.
:param kwargs: Any agent-specific key-word args to be passed.
"""
time_steps = self._training_config.num_steps
episodes = self._training_config.num_episodes
time_steps = self._training_config.num_eval_steps
episodes = self._training_config.num_eval_episodes
self._env.set_as_eval()
self.is_eval = True
if deterministic: