Loading deepchem/rl/a3c.py +1 −1 Original line number Diff line number Diff line Loading @@ -504,7 +504,7 @@ class _Worker(object): 1] += self.a3c.discount_factor * self.a3c.advantage_lambda * advantages[ j] # Record the actions, computing to one-hot if necessary. # Record the actions, converting to one-hot if necessary. actions_matrix = [] if self.a3c.continuous: Loading deepchem/rl/tests/test_a3c.py +1 −1 Original line number Diff line number Diff line Loading @@ -260,7 +260,7 @@ class TestA3C(unittest.TestCase): self._terminated = (self.count == 10) return reward # A simple policy with two hidden layers. # A simple policy with no hidden layers. class TestPolicy(dc.rl.Policy): Loading Loading
deepchem/rl/a3c.py +1 −1 Original line number Diff line number Diff line Loading @@ -504,7 +504,7 @@ class _Worker(object): 1] += self.a3c.discount_factor * self.a3c.advantage_lambda * advantages[ j] # Record the actions, computing to one-hot if necessary. # Record the actions, converting to one-hot if necessary. actions_matrix = [] if self.a3c.continuous: Loading
deepchem/rl/tests/test_a3c.py +1 −1 Original line number Diff line number Diff line Loading @@ -260,7 +260,7 @@ class TestA3C(unittest.TestCase): self._terminated = (self.count == 10) return reward # A simple policy with two hidden layers. # A simple policy with no hidden layers. class TestPolicy(dc.rl.Policy): Loading
