Skip to content

take dt into account for OU noise #197

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
zacwellmer wants to merge 1 commit into
base: master
Choose a base branch
from
Open

take dt into account for OU noise #197

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
7 changes: 4 additions & 3 deletions rllab/exploration_strategies/ou_strategy.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,13 +16,14 @@ class OUStrategy(ExplorationStrategy, Serializable):
where Wt denotes the Wiener process
"""

def __init__(self, env_spec, mu=0, theta=0.15, sigma=0.3, **kwargs):
def __init__(self, env_spec, mu=0, theta=0.15, sigma=0.3, dt=1e-2, **kwargs):
assert isinstance(env_spec.action_space, Box)
assert len(env_spec.action_space.shape) == 1
Serializable.quick_init(self, locals())
self.mu = mu
self.theta = theta
self.sigma = sigma
self.dt = dt
self.action_space = env_spec.action_space
self.state = np.ones(self.action_space.flat_dim) * self.mu
self.reset()
Expand All @@ -39,10 +40,10 @@ def __setstate__(self, d):
@overrides
def reset(self):
self.state = np.ones(self.action_space.flat_dim) * self.mu

def evolve_state(self):
x = self.state
dx = self.theta * (self.mu - x) + self.sigma * nr.randn(len(x))
dx = self.theta * (self.mu - x) * self.dt + self.sigma * np.sqrt(self.dt) * nr.randn(len(x))
self.state = x + dx
return self.state

Expand Down