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

Enlarge #2

Open
wants to merge 148 commits into
base: main
Choose a base branch
from
Open

Enlarge #2

wants to merge 148 commits into from

Conversation

LiangZhisama
Copy link

No description provided.

CaesarAndylaw and others added 30 commits February 28, 2023 15:21
@CaesarAndylaw
customization to train with safetygym
2829001
@CaesarAndylaw
headless video rendering implementation
ea36361
@CaesarAndylaw
commented
87c3f93
@CaesarAndylaw
new logger for EpCost, new train safetygym that includes cpo, working…
558698f 
… with cpo
@ruichen-v
add qp solution and line search
84301dd
@ruichen-v
add extra python path
bd63cc6
@CaesarAndylaw
run time logger implementation, CPO replay buffer, CPO training main …
5e24a61 
…loop, CPO networks, and CPO policy update
@CaesarAndylaw
Merge remote-tracking branch 'origin/ruic_dev' into main
6a089a0
@CaesarAndylaw
fix the minor implementation bugs with logger, network, cpo, and main…
d2dba34 
… training loop
@CaesarAndylaw
initial implementation for CPO, and initial experiments
6995617
@CaesarAndylaw
successfully train the vanilla policy gradient for reward
193a2b7
@CaesarAndylaw
switch to an existing pytorch implementation of vanilla policy gradie…
6c8d0cf 
…nt, the core utility function is copiedfrom spinngup implementation
@CaesarAndylaw
implementation of ppo, vpg with gpu training loop
b7b0053
@CaesarAndylaw
trpo implementation completed
173d78a
@CaesarAndylaw
before meerge
a66e8f6
@ruichen-v
add buf for cpo
dc99116
@CaesarAndylaw
Core implementation for CPO, the update function
5fb42e1
@CaesarAndylaw
fix extra char
0e4e655
@CaesarAndylaw
Merge remote-tracking branch 'origin/ruic_dev' into trpo_test_reward
2a6a4d2
@CaesarAndylaw
merged cpo buf
cc72d87
@CaesarAndylaw
complete version of spinup implementation of constrained policy optim…
7052624 
…ization, trust region policy optimization
@CaesarAndylaw
remove results
3bfbf4c
@CaesarAndylaw
remove results
182fc6e
@YIFANSUN98
add safety-gym-arm
d1354b9
@CaesarAndylaw
update the plot function to consider the cost rate
b857651
@CaesarAndylaw
update safety gym arm environment. include safety gym arm environment…
05b1058 
… into PPO and TRPO training
@CaesarAndylaw
policy model visualization is constructed for PPO
a5a5627
@YIFANSUN98
add arm model with 3 joints
d6193e7
@CaesarAndylaw
cpo and trpo video recorder
3b0d613
@CaesarAndylaw
select maximum epoch for trpo video recorder
e2ee555
waynekyrie and others added 30 commits April 26, 2023 16:45
@waynekyrie
pdo psuedo
6a6cb5c
@waynekyrie
update
12ff5c8
@waynekyrie
pdo running
a423402
@waynekyrie
update
77591c4
@waynekyrie
lpg
8afb3ee
@CaesarAndylaw
the final implementation of SCPO NIPS
29cfc57
@CaesarAndylaw
stable version of SCPO, little fix of the hopper xml
8f25f5f
@YIFANSUN98
update xml files
452881d
@YIFANSUN98
merge to main with new xml
1274e0c
@waynekyrie
Merge branch 'main' into pdo
3585f95
@waynekyrie
pdo
5f85421
@waynekyrie
Merge branch 'pdo' of https://github.com/intelligent-control-lab/safe…
e43ece0 
…_rl_bench into pdo
@waynekyrie
pdo
a1b86be
@CaesarAndylaw
stable implementation of lpg and pdo
8f5d371
@CaesarAndylaw
.gitignore is now working
19e8587
@CaesarAndylaw
.gitignore is now working
7be79f8
@YIFANSUN98
update xmls and configurations for benchmark
c50fefb
@YIFANSUN98
merge to main
878fd15
@waynekyrie
update lpg
df3240d
@waynekyrie
update lpg
f5b59a8
@CaesarAndylaw
before release, code completed
2af63f5
@CaesarAndylaw
guard_paper_version
aeb9701
Add APO; Update TRPO
07456c2
Add A2C and PPO
50249c7
Update: readme
ec69e17
Update: readme
f25c0ae
Add ISSA and fix some bugs
8d114e8
Update: about issa video generation
b289d32
@YIFANSUN98
Add: ISSA
843b012
@YIFANSUN98
Update: readme
ea49a14
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
7 participants
@LiangZhisama @CaesarAndylaw @ruichen-v @YIFANSUN98 @Vinnie6167 @Wei-TianHao @waynekyrie