forked from PaddlePaddle/PARL
-
Notifications
You must be signed in to change notification settings - Fork 0
/
mujoco_model.py
91 lines (71 loc) · 2.69 KB
/
mujoco_model.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
# Copyright (c) 2018 PaddlePaddle Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import paddle.fluid as fluid
import parl
from parl import layers
class MujocoModel(parl.Model):
def __init__(self, act_dim, max_action):
self.actor_model = ActorModel(act_dim, max_action)
self.critic_model = CriticModel()
def policy(self, obs):
return self.actor_model.policy(obs)
def value(self, obs, act):
return self.critic_model.value(obs, act)
def Q1(self, obs, act):
return self.critic_model.Q1(obs, act)
def get_actor_params(self):
return self.actor_model.parameters()
class ActorModel(parl.Model):
def __init__(self, act_dim, max_action):
hid1_size = 400
hid2_size = 300
self.fc1 = layers.fc(size=hid1_size, act='relu')
self.fc2 = layers.fc(size=hid2_size, act='relu')
self.fc3 = layers.fc(size=act_dim, act='tanh')
self.max_action = max_action
def policy(self, obs):
hid1 = self.fc1(obs)
hid2 = self.fc2(hid1)
means = self.fc3(hid2)
means = means * self.max_action
return means
class CriticModel(parl.Model):
def __init__(self):
hid1_size = 400
hid2_size = 300
self.fc1 = layers.fc(size=hid1_size, act='relu')
self.fc2 = layers.fc(size=hid2_size, act='relu')
self.fc3 = layers.fc(size=1, act=None)
self.fc4 = layers.fc(size=hid1_size, act='relu')
self.fc5 = layers.fc(size=hid2_size, act='relu')
self.fc6 = layers.fc(size=1, act=None)
def value(self, obs, act):
hid1 = self.fc1(obs)
concat1 = layers.concat([hid1, act], axis=1)
Q1 = self.fc2(concat1)
Q1 = self.fc3(Q1)
Q1 = layers.squeeze(Q1, axes=[1])
hid2 = self.fc4(obs)
concat2 = layers.concat([hid2, act], axis=1)
Q2 = self.fc5(concat2)
Q2 = self.fc6(Q2)
Q2 = layers.squeeze(Q2, axes=[1])
return Q1, Q2
def Q1(self, obs, act):
hid1 = self.fc1(obs)
concat1 = layers.concat([hid1, act], axis=1)
Q1 = self.fc2(concat1)
Q1 = self.fc3(Q1)
Q1 = layers.squeeze(Q1, axes=[1])
return Q1