wassname/ray
1
0
Fork 0
mirror of https://github.com/wassname/ray.git synced 2026-07-31 12:41:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

Revert "[wingman -> rllib] IMPALA MultiDiscrete changes (#3967)" (#4332)

Browse Source 
This reverts commit 962b17f567.
This commit is contained in:
Eric Liang
2019-03-11 22:51:26 -07:00
committed by GitHub
parent 7ff56ce826
commit 3c41cb9b60
8 changed files with 131 additions and 658 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/ray/rllib/models/action_dist.py
-25
View File
@@ -114,31 +114,6 @@ class Categorical(ActionDistribution):
return tf.squeeze(tf.multinomial(self.inputs, 1), axis=1)
class MultiCategorical(ActionDistribution):
"""Categorical distribution for discrete action spaces."""
def __init__(self, inputs):
self.cats = [Categorical(input_) for input_ in inputs]
self.sample_op = self._build_sample_op()
def logp(self, actions):
# If tensor is provided, unstack it into list
if isinstance(actions, tf.Tensor):
actions = tf.unstack(actions, axis=1)
logps = tf.stack(
[cat.logp(act) for cat, act in zip(self.cats, actions)])
return tf.reduce_sum(logps, axis=0)
def entropy(self):
return tf.stack([cat.entropy() for cat in self.cats], axis=1)
def kl(self, other):
return [cat.kl(oth_cat) for cat, oth_cat in zip(self.cats, other.cats)]
def _build_sample_op(self):
return tf.stack([cat.sample() for cat in self.cats], axis=1)
class DiagGaussian(ActionDistribution):
"""Action distribution where each vector element is a gaussian.