Skip to content

Error message when using ODD and Curiosity #883

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

Merged
merged 2 commits into from
Jun 16, 2018
Merged

Error message when using ODD and Curiosity #883

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2b65274
Remove extra bouncer brain hyperparameters
awjuliani Jun 16, 2018
849066d
Add error when using curiosity+odd
awjuliani Jun 16, 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
6 changes: 0 additions & 6 deletions python/trainer_config.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -130,12 +130,6 @@ Ball3DHardBrain:
gamma: 0.995
beta: 0.001

BouncerBrain:
normalize: true
max_steps: 5.0e5
num_layers: 2
hidden_units: 56

TennisBrain:
normalize: true

Expand Down
3 changes: 3 additions & 0 deletions python/unitytrainers/ppo/trainer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -204,6 +204,9 @@ def generate_intrinsic_rewards(self, curr_info, next_info):
:return: Intrinsic rewards for all agents.
"""
if self.use_curiosity:
if curr_info.agents != next_info.agents:
raise UnityTrainerException("Training with Curiosity-driven exploration"
" and On-Demand Decision making is currently not supported.")
feed_dict = {self.model.batch_size: len(curr_info.vector_observations), self.model.sequence_length: 1}
if self.is_continuous_action:
feed_dict[self.model.output] = next_info.previous_vector_actions
Expand Down