issues
search
google-deepmind
/
acme
A library of reinforcement learning components and agents
Apache License 2.0
3.52k
stars
426
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Is it possible to run mompo for discrete and continuous action spaces?
#272
Nahid-Quader
opened
2 years ago
0
New Release
#271
cemlyn007
opened
2 years ago
3
MPO temperature updates
#270
henry-prior
closed
2 years ago
4
Low SPS with `run_impala.py`
#269
vwxyzjn
closed
1 year ago
7
Reverb is not compatible with Windows
#268
FinAminToastCrunch
closed
2 years ago
1
Errors while running DistributedD4PG
#267
kmukeshreddy
closed
3 months ago
33
Changes in gym step and reset
#266
rdevon
closed
2 years ago
3
Regarding controlled runs for D4PG lp.launch
#265
kmukeshreddy
closed
2 years ago
0
Basic SAC cartpole example fails: unexpected keyword argument 'minimum'
#264
rdevon
closed
2 years ago
2
Number of steps per second (Steps Per Second) for D4PG Agent
#263
kmukeshreddy
closed
2 years ago
0
The Tutorial part should update
#262
ruyikang
closed
2 years ago
3
Add meltingpot MultiagentDictKeyWrapper support
#261
alan-cooney
opened
2 years ago
0
Fix the quickstart notebook
#260
alan-cooney
closed
2 years ago
1
Wrong recurrent state accessed in R2D2 Learner
#259
ostap-viniavskyi
closed
2 years ago
1
Problems with MBOP in offline examples
#258
ZhengyaoJiang
opened
2 years ago
0
Stupid question: Where do the 'objectives' go in the MOMPO model?
#257
MotorCityCobra
opened
2 years ago
0
run_experiment allow different seeded/wrapped environments for train and eval
#256
Andrewzh112
closed
2 years ago
2
Regarding Seed for tf rl agents in acme
#255
kmukeshreddy
opened
2 years ago
3
pip install dm-acme[jax] has problem
#254
ruyikang
closed
2 years ago
2
Regarding the papers "What Matters for Adversarial Imitation Learning?"
#253
nuomizai
closed
2 years ago
2
pip install error
#252
lukaemon
closed
2 years ago
1
Use typing.Mapping instead of collections.abc.Mapping
#251
ethanluoyc
opened
2 years ago
0
what is the helpers library
#250
Mo379
closed
2 years ago
2
Fix policy loss gradient in TD3
#249
ethanluoyc
opened
2 years ago
1
error running DQN example in distributed setting
#248
kinalmehta
closed
2 years ago
1
Cannot add extras to reverb adder
#247
cop4587
closed
2 years ago
0
Regarding Hyperparameter Search for acme tf agents (d4pg, dmpo)
#246
kmukeshreddy
opened
2 years ago
0
Qestion about updating the agent
#245
ZixuanLiu4869
opened
2 years ago
5
How to use in "production"?
#244
sguysc
closed
2 years ago
6
Understanding setting Reverb dataset parameters
#243
ethanluoyc
closed
2 years ago
4
dm-launchpad not available for Mac OS
#242
kmukeshreddy
closed
2 years ago
1
BUGFIX: Unpin tensorflow_datasets
#241
ethanluoyc
opened
2 years ago
3
Issue when import acme
#240
JiaojiaoYe1994
closed
2 years ago
2
Question about R2D2 loss, masking, and episode boundaries
#239
wcarvalho
closed
2 years ago
2
Add py.typed
#238
ethanluoyc
opened
2 years ago
1
Improving snapshotting in JAX distributed experiments
#237
ethanluoyc
opened
2 years ago
8
run_dqn demo fails with distributed training: ValueError: TrajectoryColumns cannot contain any None data references
#236
rdevon
opened
2 years ago
6
Segmentation fault in using the new version of LocalLayout
#235
ethanluoyc
closed
2 years ago
8
RuntimeError: 'replay' nodes were not serializable
#234
neardws
closed
2 years ago
6
New LocalLayout may deadlock block on sample
#233
ethanluoyc
closed
2 years ago
36
Log rewards statistics in SAC agents.
#232
wookayin
opened
2 years ago
2
Use num_batch_dims=0 to deal with observations containing scalars
#231
wookayin
opened
2 years ago
1
Example of using tfrecord logger to use acme with tensorboard
#230
rdevon
opened
2 years ago
7
Release `wrappers` as PyPI package
#229
kevinzakka
closed
1 year ago
6
ClippedGaussian wrong thing is clipped
#228
ahsimb
closed
2 years ago
1
Checkpoints aren't saved by default and distributed layout?
#227
wcarvalho
closed
2 years ago
1
Regarding controlled runs for D4PG lp.launch
#226
kmukeshreddy
closed
2 years ago
4
lp.launch error: psutil.NoSuchProcess process no longer exists (pid=499)
#225
kmukeshreddy
closed
2 years ago
5
fix: Update version of reverb & launchpad to work with distributed ppo.
#224
KaleabTessera
closed
2 years ago
1
JAX PPO implementation incompatible with reverb 0.7.1
#223
kinalmehta
closed
2 years ago
1
Previous
Next