gaspersic/baselines
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

export: fix accidental rename

Browse Source
This commit is contained in:
Christopher Hesse
2018-02-14 22:01:16 -08:00
parent edb52c22a5
commit df2e846ab7
2 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
baselines/acer/acer_simple.py
View File

@@ -243,7 +243,7 @@ class Runner(object):
mb_mus.append(mus) mb_mus.append(mus)
mb_dones.append(self.dones) mb_dones.append(self.dones)
obs, rewards, dones, _ = self.env.step(actions) obs, rewards, dones, _ = self.env.step(actions)
# states information for statefull predictors like LSTM # states information for statefull models like LSTM
self.states = states self.states = states
self.dones = dones self.dones = dones
self.update_obs(obs, dones) self.update_obs(obs, dones)
@@ -260,7 +260,7 @@ class Runner(object):
mb_dones = np.asarray(mb_dones, dtype=np.bool).swapaxes(1, 0) mb_dones = np.asarray(mb_dones, dtype=np.bool).swapaxes(1, 0)
mb_masks = mb_dones # Used for statefull predictors like LSTM's to mask state when done mb_masks = mb_dones # Used for statefull models like LSTM's to mask state when done
mb_dones = mb_dones[:, 1:] # Used for calculating returns. The dones array is now aligned with rewards mb_dones = mb_dones[:, 1:] # Used for calculating returns. The dones array is now aligned with rewards
# shapes are now [nenv, nsteps, []] # shapes are now [nenv, nsteps, []]

2
baselines/acktr/kfac.py
View File

@@ -134,7 +134,7 @@ class KfacOptimizer():
# check associated weights and bias for homogeneous coordinate representation # check associated weights and bias for homogeneous coordinate representation
# and check redundent factors # and check redundent factors
# TO-DO: there may be a bug to detect associate bias and weights for # TO-DO: there may be a bug to detect associate bias and weights for
# forking layer, e.g. in inception predictors. # forking layer, e.g. in inception models.
for param in varlist: for param in varlist:
factorTensors[param]['assnWeights'] = None factorTensors[param]['assnWeights'] = None
factorTensors[param]['assnBias'] = None factorTensors[param]['assnBias'] = None