evolutionary-policy-optimization 0.0.71__py3-none-any.whl → 0.0.72__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- evolutionary_policy_optimization/epo.py +6 -1
- {evolutionary_policy_optimization-0.0.71.dist-info → evolutionary_policy_optimization-0.0.72.dist-info}/METADATA +1 -1
- {evolutionary_policy_optimization-0.0.71.dist-info → evolutionary_policy_optimization-0.0.72.dist-info}/RECORD +5 -5
- {evolutionary_policy_optimization-0.0.71.dist-info → evolutionary_policy_optimization-0.0.72.dist-info}/WHEEL +0 -0
- {evolutionary_policy_optimization-0.0.71.dist-info → evolutionary_policy_optimization-0.0.72.dist-info}/licenses/LICENSE +0 -0
|
@@ -1281,9 +1281,14 @@ class EPO(Module):
|
|
|
1281
1281
|
self,
|
|
1282
1282
|
agent: Agent,
|
|
1283
1283
|
env,
|
|
1284
|
-
num_learning_cycles
|
|
1284
|
+
num_learning_cycles,
|
|
1285
|
+
seed = None
|
|
1285
1286
|
):
|
|
1286
1287
|
|
|
1288
|
+
if exists(seed):
|
|
1289
|
+
torch.manual_seed(seed)
|
|
1290
|
+
np.random.seed(seed)
|
|
1291
|
+
|
|
1287
1292
|
for _ in tqdm(range(num_learning_cycles), desc = 'learning cycle'):
|
|
1288
1293
|
|
|
1289
1294
|
memories = self.gather_experience_from(env)
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: evolutionary-policy-optimization
|
|
3
|
-
Version: 0.0.
|
|
3
|
+
Version: 0.0.72
|
|
4
4
|
Summary: EPO - Pytorch
|
|
5
5
|
Project-URL: Homepage, https://pypi.org/project/evolutionary-policy-optimization/
|
|
6
6
|
Project-URL: Repository, https://github.com/lucidrains/evolutionary-policy-optimization
|
|
@@ -1,9 +1,9 @@
|
|
|
1
1
|
evolutionary_policy_optimization/__init__.py,sha256=0q0aBuFgWi06MLMD8FiHzBYQ3_W4LYWrwmCtF3u5H2A,201
|
|
2
2
|
evolutionary_policy_optimization/distributed.py,sha256=7KgZdeS_wxBHo_du9XZFB1Cu318J-Bp66Xdr6Log_20,2423
|
|
3
|
-
evolutionary_policy_optimization/epo.py,sha256=
|
|
3
|
+
evolutionary_policy_optimization/epo.py,sha256=h_BaNLFeU5SfVaOcVeMdEdjfYop6enOPAsESQWZflfA,39449
|
|
4
4
|
evolutionary_policy_optimization/experimental.py,sha256=-IgqjJ_Wk_CMB1y9YYWpoYqTG9GZHAS6kbRdTluVevg,1563
|
|
5
5
|
evolutionary_policy_optimization/mock_env.py,sha256=QhPYIazU3uFPKTMZyFw70KhXiDUBr5aU3v1idotfVFI,1391
|
|
6
|
-
evolutionary_policy_optimization-0.0.
|
|
7
|
-
evolutionary_policy_optimization-0.0.
|
|
8
|
-
evolutionary_policy_optimization-0.0.
|
|
9
|
-
evolutionary_policy_optimization-0.0.
|
|
6
|
+
evolutionary_policy_optimization-0.0.72.dist-info/METADATA,sha256=kZZupJU1gYm6MEmDYB2D-gIF2NZsAY4qcK9Z5pAT1mQ,6304
|
|
7
|
+
evolutionary_policy_optimization-0.0.72.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
|
|
8
|
+
evolutionary_policy_optimization-0.0.72.dist-info/licenses/LICENSE,sha256=1yCiA9b5nhslTavxPjsQAO-wpOnwJR9-l8LTVi7GJuk,1066
|
|
9
|
+
evolutionary_policy_optimization-0.0.72.dist-info/RECORD,,
|
|
File without changes
|