Skip to content

inconsistency fix for stochastic deep sea #33

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
cgao3 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

inconsistency fix for stochastic deep sea #33

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
5 changes: 3 additions & 2 deletions bsuite/environments/deep_sea.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -118,11 +118,12 @@ def _step(self, action: int) -> dm_env.TimeStep:
action_right = action == self._action_mapping[self._row, self._column]

# Reward calculation
if self._column == self._size - 1 and action_right:
if self._column == self._size - 1 and action_right \
and (self._rng.rand() > 1 / self._size or self._deterministic):
reward += 1.
self._denoised_return += 1.
if not self._deterministic: # Noisy rewards on the 'end' of chain.
if self._row == self._size - 1 and self._column in [0, self._size - 1]:
if self._row == self._size - 1 and 0 <= self._column <= self._size - 1:
reward += self._rng.randn()

# Transition dynamics
Expand Down