issues
search
vlad17
/
mve
MVE: model-based value estimation
Apache License 2.0
10
stars
0
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
add new run experiments
#408
vlad17
closed
5 years ago
0
markovian termination condition
#407
vlad17
closed
6 years ago
0
scale obs too
#406
vlad17
closed
6 years ago
0
rm q pre-scaling
#405
vlad17
closed
6 years ago
0
Preprocess acs
#404
vlad17
closed
6 years ago
0
allow disabling normalization
#403
vlad17
closed
6 years ago
0
reset dyn default
#402
vlad17
closed
6 years ago
0
update gym compat (#300)
#401
normster
opened
6 years ago
0
Locks2 -- lock harder
#400
vlad17
closed
6 years ago
0
kill locks
#399
vlad17
closed
6 years ago
0
allow multiple experiments at once
#398
vlad17
closed
6 years ago
0
Masks for early stop
#397
vlad17
closed
6 years ago
0
start snoozed
#396
vlad17
closed
6 years ago
0
remove scaling
#395
vlad17
closed
6 years ago
0
dynamics plotting bells and whistles
#394
vlad17
closed
6 years ago
0
added reparam trick
#393
vlad17
closed
6 years ago
0
no summary reporting
#392
vlad17
closed
6 years ago
0
changed defaults
#391
vlad17
closed
6 years ago
0
dynamics normalization only
#390
vlad17
closed
6 years ago
0
create stable online quantile clipping
#389
vlad17
opened
6 years ago
0
Add reward scaling / popart
#388
vlad17
opened
6 years ago
0
make memory folder and add normalization
#387
vlad17
closed
6 years ago
0
Ddpg dynamics plot
#386
vlad17
closed
6 years ago
0
miscellaneous cleanup
#385
vlad17
closed
6 years ago
0
create a separate parameter-space noise module
#384
vlad17
opened
6 years ago
0
create a separate imaginary buffer module
#383
vlad17
opened
6 years ago
0
merge SACLearner into SAC class
#382
vlad17
opened
6 years ago
0
merge DDPGLearner into DDPG class
#381
vlad17
opened
6 years ago
0
remove experiment main
#380
vlad17
closed
6 years ago
0
miscellaneous installation and rendering setup
#379
vlad17
closed
6 years ago
0
remove experiment main
#378
vlad17
closed
6 years ago
0
make hooks reporter-specific
#377
vlad17
opened
6 years ago
0
rename horizon as rollout_horizon
#376
vlad17
opened
6 years ago
0
Fix flags
#375
vlad17
closed
6 years ago
0
Rm optimizer
#374
vlad17
closed
6 years ago
0
Tolerant logging (if files change, then logger no longer throws)
#373
vlad17
closed
6 years ago
0
centralized dynamics metrics
#372
vlad17
closed
6 years ago
0
switch to absl-py gflags
#371
vlad17
opened
6 years ago
0
use agent/learner interface and a common rl loop to express computation
#370
vlad17
closed
6 years ago
0
Rm poster and report dirs
#369
vlad17
closed
6 years ago
0
Rm cmpc
#368
vlad17
closed
6 years ago
0
added async hyperband
#367
vlad17
closed
6 years ago
0
make server port configureable for ray tune with --server_port
#366
vlad17
closed
6 years ago
0
Add MVE To SAC
#365
vlad17
closed
6 years ago
0
when performing MVE do the critic eval in a single op
#364
vlad17
closed
6 years ago
0
Unify ddpg sac interfaces, SAC-compatible envs
#363
vlad17
closed
6 years ago
0
Add SAC implementation w/o MVE
#362
vlad17
closed
6 years ago
0
Add SAC
#361
vlad17
closed
6 years ago
0
git hash shouldn't be a flag
#360
vlad17
closed
6 years ago
0
Normalization techniques
#359
vlad17
closed
6 years ago
3
Next