Skip to content

add act_with_exploration() method #298

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 3 commits into
base: master
Choose a base branch
from
Open

add act_with_exploration() method #298

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
1e26af7
add act_with_exploration() method
Aug 17, 2018
4dbc6d6
corrected style to pass flake8
Aug 17, 2018
3db0754
self.t update added
Aug 17, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
26 changes: 23 additions & 3 deletions chainerrl/agents/dqn.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -352,19 +352,39 @@ def _compute_loss(self, exp_batch, gamma, errors_out=None):
return compute_value_loss(y, t, clip_delta=self.clip_delta,
batch_accumulator=self.batch_accumulator)

def act(self, obs):
def act_with_exploration(self, obs):

with chainer.using_config('train', False):
with chainer.no_backprop_mode():
action_value = self.model(
self.batch_states([obs], self.xp, self.phi))
q = float(action_value.max.data)
action = cuda.to_cpu(action_value.greedy_actions.data)[0]

greedy_action = cuda.to_cpu(action_value.greedy_actions.data)[0]

action = self.explorer.select_action(self.t,
lambda: greedy_action,
action_value=action_value)
self.t += 1
# Update stats
self.average_q *= self.average_q_decay
self.average_q += (1 - self.average_q_decay) * q

self.logger.debug('t:%s q:%s action_value:%s', self.t, q, action_value)
return action

def act(self, obs):
with chainer.using_config('train', False):
with chainer.no_backprop_mode():
action_value = self.model(
self.batch_states([obs], self.xp, self.phi))
q = float(action_value.max.data)
action = cuda.to_cpu(action_value.greedy_actions.data)[0]

# Update stats
self.average_q *= self.average_q_decay
self.average_q += (1 - self.average_q_decay) * q

self.logger.debug('t:%s q:%s action_value:%s', self.t, q, action_value)
return action

def act_and_train(self, obs, reward):
Expand Down