Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

增加SAC在Ant-v4和Acrobot-v1下的benchmark #60

Open
wants to merge 7 commits into
base: main
Choose a base branch
from
Open

增加SAC在Ant-v4和Acrobot-v1下的benchmark #60

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
3ec3d75
增加SAC在Ant-v4和Acrobot-v1下的benchmark
Katniss1025 Apr 30, 2023
5d301dc
Merge branch 'johnjim0816:main' into main
Katniss1025 May 23, 2023
af2ade0
Merge branch 'johnjim0816:main' into main
Katniss1025 May 29, 2023
0e0f29d
notebook for SAC_D
Katniss1025 May 29, 2023
7b60d5b
Merge branch 'johnjim0816:main' into main
Katniss1025 May 31, 2023
9aa5a9b
Merge branch 'johnjim0816:main' into main
Katniss1025 Jun 6, 2023
614bc83
Merge branch 'johnjim0816:main' into main
Katniss1025 Jun 7, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
39 changes: 39 additions & 0 deletions benchmarks/Acrobot-v1/Test_gym_SAC_D_20230427-145128/config.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,39 @@
general_cfg:
algo_name: SAC_D
continous: true
device: cpu
env_name: gym
eval_eps: 10
eval_per_episode: 5
load_checkpoint: true
load_path: Train_gym_SAC_D_20230427-130926
max_steps: 200
mode: test
mp_backend: mp
new_step_api: true
render: true
render_mode: rgb_array
save_fig: true
seed: 0
show_fig: false
test_eps: 200
train_eps: 1000
wrapper: null
algo_cfg:
alpha: 0.1
automatic_entropy_tuning: false
batch_size: 64
buffer_size: 1000000
epsilon_decay: 500
epsilon_end: 0.01
epsilon_start: 0.95
gamma: 0.99
hidden_dim: 256
lr: 0.001
n_epochs: 1
target_update: 1
tau: 0.005
env_cfg:
id: Acrobot-v1
new_step_api: true
render_mode: null
247 changes: 247 additions & 0 deletions benchmarks/Acrobot-v1/Test_gym_SAC_D_20230427-145128/logs/log.txt
View file
Open in desktop

Large diffs are not rendered by default.

Binary file added benchmarks/Acrobot-v1/Test_gym_SAC_D_20230427-145128/models/checkpoint.pt
View file
Open in desktop
Binary file not shown.
Binary file added benchmarks/Acrobot-v1/Test_gym_SAC_D_20230427-145128/results/learning_curve.png
View file
Open in desktop
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
201 changes: 201 additions & 0 deletions benchmarks/Acrobot-v1/Test_gym_SAC_D_20230427-145128/results/res.csv
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,201 @@
episodes,rewards,steps
0,-91.0,92
1,-86.0,87
2,-86.0,87
3,-101.0,102
4,-86.0,87
5,-146.0,147
6,-126.0,127
7,-105.0,106
8,-88.0,89
9,-84.0,85
10,-99.0,100
11,-81.0,82
12,-79.0,80
13,-85.0,86
14,-138.0,139
15,-82.0,83
16,-106.0,107
17,-75.0,76
18,-93.0,94
19,-82.0,83
20,-76.0,77
21,-94.0,95
22,-89.0,90
23,-64.0,65
24,-96.0,97
25,-82.0,83
26,-101.0,102
27,-111.0,112
28,-91.0,92
29,-92.0,93
30,-81.0,82
31,-99.0,100
32,-92.0,93
33,-82.0,83
34,-87.0,88
35,-101.0,102
36,-82.0,83
37,-149.0,150
38,-80.0,81
39,-98.0,99
40,-81.0,82
41,-139.0,140
42,-87.0,88
43,-99.0,100
44,-95.0,96
45,-126.0,127
46,-200.0,200
47,-81.0,82
48,-100.0,101
49,-136.0,137
50,-79.0,80
51,-106.0,107
52,-78.0,79
53,-114.0,115
54,-78.0,79
55,-84.0,85
56,-79.0,80
57,-114.0,115
58,-79.0,80
59,-86.0,87
60,-79.0,80
61,-85.0,86
62,-81.0,82
63,-79.0,80
64,-91.0,92
65,-96.0,97
66,-168.0,169
67,-87.0,88
68,-124.0,125
69,-100.0,101
70,-200.0,200
71,-106.0,107
72,-200.0,200
73,-78.0,79
74,-88.0,89
75,-95.0,96
76,-83.0,84
77,-100.0,101
78,-109.0,110
79,-82.0,83
80,-93.0,94
81,-93.0,94
82,-81.0,82
83,-102.0,103
84,-83.0,84
85,-98.0,99
86,-100.0,101
87,-82.0,83
88,-92.0,93
89,-103.0,104
90,-90.0,91
91,-82.0,83
92,-81.0,82
93,-101.0,102
94,-96.0,97
95,-77.0,78
96,-87.0,88
97,-82.0,83
98,-114.0,115
99,-98.0,99
100,-89.0,90
101,-104.0,105
102,-96.0,97
103,-84.0,85
104,-82.0,83
105,-78.0,79
106,-101.0,102
107,-80.0,81
108,-82.0,83
109,-78.0,79
110,-137.0,138
111,-81.0,82
112,-95.0,96
113,-85.0,86
114,-86.0,87
115,-96.0,97
116,-83.0,84
117,-91.0,92
118,-81.0,82
119,-136.0,137
120,-83.0,84
121,-85.0,86
122,-97.0,98
123,-89.0,90
124,-78.0,79
125,-80.0,81
126,-100.0,101
127,-81.0,82
128,-88.0,89
129,-99.0,100
130,-94.0,95
131,-80.0,81
132,-91.0,92
133,-97.0,98
134,-81.0,82
135,-90.0,91
136,-105.0,106
137,-100.0,101
138,-97.0,98
139,-106.0,107
140,-109.0,110
141,-80.0,81
142,-90.0,91
143,-89.0,90
144,-102.0,103
145,-104.0,105
146,-82.0,83
147,-80.0,81
148,-106.0,107
149,-101.0,102
150,-98.0,99
151,-96.0,97
152,-99.0,100
153,-81.0,82
154,-81.0,82
155,-82.0,83
156,-81.0,82
157,-81.0,82
158,-83.0,84
159,-97.0,98
160,-84.0,85
161,-81.0,82
162,-98.0,99
163,-91.0,92
164,-92.0,93
165,-82.0,83
166,-84.0,85
167,-90.0,91
168,-100.0,101
169,-81.0,82
170,-81.0,82
171,-86.0,87
172,-87.0,88
173,-85.0,86
174,-82.0,83
175,-84.0,85
176,-93.0,94
177,-171.0,172
178,-98.0,99
179,-146.0,147
180,-90.0,91
181,-116.0,117
182,-81.0,82
183,-92.0,93
184,-82.0,83
185,-82.0,83
186,-102.0,103
187,-93.0,94
188,-96.0,97
189,-200.0,200
190,-98.0,99
191,-80.0,81
192,-98.0,99
193,-87.0,88
194,-87.0,88
195,-75.0,76
196,-157.0,158
197,-86.0,87
198,-88.0,89
199,-86.0,87
39 changes: 39 additions & 0 deletions benchmarks/Acrobot-v1/Train_gym_SAC_D_20230427-130926/config.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,39 @@
general_cfg:
algo_name: SAC_D
continous: true
device: cpu
env_name: gym
eval_eps: 10
eval_per_episode: 5
load_checkpoint: false
load_path: Train_gym_SAC_D_20230426-160259
max_steps: 200
mode: train
mp_backend: mp
new_step_api: true
render: true
render_mode: human
save_fig: true
seed: 0
show_fig: false
test_eps: 200
train_eps: 1000
wrapper: null
algo_cfg:
alpha: 0.1
automatic_entropy_tuning: false
batch_size: 64
buffer_size: 1000000
epsilon_decay: 500
epsilon_end: 0.01
epsilon_start: 0.95
gamma: 0.99
hidden_dim: 256
lr: 0.001
n_epochs: 1
target_update: 1
tau: 0.005
env_cfg:
id: Acrobot-v1
new_step_api: true
render_mode: null
Loading