evolutionary-policy-optimization 0.1.0__py3-none-any.whl → 0.1.1__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/__init__.py +4 -0
- evolutionary_policy_optimization/env_wrappers.py +36 -0
- evolutionary_policy_optimization/epo.py +1 -0
- {evolutionary_policy_optimization-0.1.0.dist-info → evolutionary_policy_optimization-0.1.1.dist-info}/METADATA +2 -1
- evolutionary_policy_optimization-0.1.1.dist-info/RECORD +10 -0
- evolutionary_policy_optimization-0.1.0.dist-info/RECORD +0 -9
- {evolutionary_policy_optimization-0.1.0.dist-info → evolutionary_policy_optimization-0.1.1.dist-info}/WHEEL +0 -0
- {evolutionary_policy_optimization-0.1.0.dist-info → evolutionary_policy_optimization-0.1.1.dist-info}/licenses/LICENSE +0 -0
@@ -0,0 +1,36 @@
|
|
1
|
+
import torch
|
2
|
+
from torch.nn import Module
|
3
|
+
|
4
|
+
from evolutionary_policy_optimization.epo import create_agent, Agent
|
5
|
+
|
6
|
+
class GymnasiumEnvWrapper(Module):
|
7
|
+
def __init__(
|
8
|
+
self,
|
9
|
+
env
|
10
|
+
):
|
11
|
+
super().__init__()
|
12
|
+
self.env = env
|
13
|
+
|
14
|
+
def reset(self, *args, **kwargs):
|
15
|
+
return self.env.reset(*args, **kwargs)
|
16
|
+
|
17
|
+
def step(self, *args, **kwargs):
|
18
|
+
return self.env.step(*args, **kwargs)
|
19
|
+
|
20
|
+
def to_agent_hparams(self):
|
21
|
+
return dict(
|
22
|
+
dim_state = self.env.observation_space.shape[0],
|
23
|
+
actor_num_actions = self.env.action_space.n
|
24
|
+
)
|
25
|
+
|
26
|
+
def to_epo_agent(
|
27
|
+
self,
|
28
|
+
*args,
|
29
|
+
**kwargs
|
30
|
+
) -> Agent:
|
31
|
+
|
32
|
+
return create_agent(
|
33
|
+
*args,
|
34
|
+
**self.to_agent_hparams(),
|
35
|
+
**kwargs
|
36
|
+
)
|
@@ -1,6 +1,6 @@
|
|
1
1
|
Metadata-Version: 2.4
|
2
2
|
Name: evolutionary-policy-optimization
|
3
|
-
Version: 0.1.
|
3
|
+
Version: 0.1.1
|
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
|
@@ -34,6 +34,7 @@ Classifier: License :: OSI Approved :: MIT License
|
|
34
34
|
Classifier: Programming Language :: Python :: 3.8
|
35
35
|
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
|
36
36
|
Requires-Python: >=3.9
|
37
|
+
Requires-Dist: accelerate
|
37
38
|
Requires-Dist: adam-atan2-pytorch
|
38
39
|
Requires-Dist: assoc-scan>=0.0.2
|
39
40
|
Requires-Dist: einops>=0.8.1
|
@@ -0,0 +1,10 @@
|
|
1
|
+
evolutionary_policy_optimization/__init__.py,sha256=NyiYDYU7DlpmOTM7xiBQET3r1WwX0ebrgMCBLSQrW3c,288
|
2
|
+
evolutionary_policy_optimization/distributed.py,sha256=7KgZdeS_wxBHo_du9XZFB1Cu318J-Bp66Xdr6Log_20,2423
|
3
|
+
evolutionary_policy_optimization/env_wrappers.py,sha256=bDL06o9_b1iW6k3fw2xifnOnYlzs643tdW6Yv2gsIdw,803
|
4
|
+
evolutionary_policy_optimization/epo.py,sha256=hxXOUt4tCmlqN2zjvG6Qfp_icq2ApuMowx3xK0Wm3wY,39498
|
5
|
+
evolutionary_policy_optimization/experimental.py,sha256=-IgqjJ_Wk_CMB1y9YYWpoYqTG9GZHAS6kbRdTluVevg,1563
|
6
|
+
evolutionary_policy_optimization/mock_env.py,sha256=TLyyRm6tOD0Kdn9QqJJQriaSnsR-YmNQHo4OohmZFG4,1410
|
7
|
+
evolutionary_policy_optimization-0.1.1.dist-info/METADATA,sha256=ToFlj-YAqNqTZx2W9LZXmhteQBBUCTO00uAFd-p9s48,6329
|
8
|
+
evolutionary_policy_optimization-0.1.1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
|
9
|
+
evolutionary_policy_optimization-0.1.1.dist-info/licenses/LICENSE,sha256=1yCiA9b5nhslTavxPjsQAO-wpOnwJR9-l8LTVi7GJuk,1066
|
10
|
+
evolutionary_policy_optimization-0.1.1.dist-info/RECORD,,
|
@@ -1,9 +0,0 @@
|
|
1
|
-
evolutionary_policy_optimization/__init__.py,sha256=0q0aBuFgWi06MLMD8FiHzBYQ3_W4LYWrwmCtF3u5H2A,201
|
2
|
-
evolutionary_policy_optimization/distributed.py,sha256=7KgZdeS_wxBHo_du9XZFB1Cu318J-Bp66Xdr6Log_20,2423
|
3
|
-
evolutionary_policy_optimization/epo.py,sha256=VrFD5lFQrS7KeYTC-WavEMTHgQXoq7vNPVXnRJwFSDI,39491
|
4
|
-
evolutionary_policy_optimization/experimental.py,sha256=-IgqjJ_Wk_CMB1y9YYWpoYqTG9GZHAS6kbRdTluVevg,1563
|
5
|
-
evolutionary_policy_optimization/mock_env.py,sha256=TLyyRm6tOD0Kdn9QqJJQriaSnsR-YmNQHo4OohmZFG4,1410
|
6
|
-
evolutionary_policy_optimization-0.1.0.dist-info/METADATA,sha256=Nl3JSTSireDXXvX1ZrMQqTA8CXz1USUQOwPuuCtgCJw,6303
|
7
|
-
evolutionary_policy_optimization-0.1.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
|
8
|
-
evolutionary_policy_optimization-0.1.0.dist-info/licenses/LICENSE,sha256=1yCiA9b5nhslTavxPjsQAO-wpOnwJR9-l8LTVi7GJuk,1066
|
9
|
-
evolutionary_policy_optimization-0.1.0.dist-info/RECORD,,
|
File without changes
|