Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / google-deepmind/acme issues and pull requests
#323 - ACME with MuJoco
Issue -
State: open - Opened by AbhayGoyal 3 months ago
#322 - Align pyproject.toml with setup.py
Pull Request -
State: closed - Opened by cnm13ryan 3 months ago
- 1 comment
#321 - Unsolvable jax dependency
Issue -
State: open - Opened by adiaconu11 6 months ago
- 2 comments
#320 - Unreasonable dependency on really old dm-control
Issue -
State: open - Opened by joaospinto 6 months ago
#319 - Agent57 or MEME
Issue -
State: open - Opened by hlsafin 6 months ago
#318 - Dependency trouble
Issue -
State: open - Opened by liuweishuo 7 months ago
#317 - Dependency trouble
Issue -
State: open - Opened by Timisorean 7 months ago
- 1 comment
#316 - Gymnasium
Issue -
State: open - Opened by balloch 10 months ago
- 1 comment
#315 - Is there a num_iterations argument in offline examples?
Issue -
State: closed - Opened by zgzhikaru 11 months ago
- 2 comments
#314 - Using Quickstart D4PG tutorial with a gpu
Issue -
State: open - Opened by davidireland3 12 months ago
#313 - Pinning dm-haiku to 0.0.10
Pull Request -
State: open - Opened by jonas-eschmann 12 months ago
- 1 comment
#312 - XM Docker distributed experiments don't finish cleanly
Issue -
State: open - Opened by JoeMWatson about 1 year ago
#311 - Use ACME with Ray Tune ASHAScheduler
Issue -
State: open - Opened by lyshuga about 1 year ago
#310 - How to launch mutil Actors on different machines?
Issue -
State: open - Opened by hilanzy about 1 year ago
#309 - Add devices params to PPO learner
Pull Request -
State: open - Opened by armandpicard about 1 year ago
#308 - Issue with ACME's Distributional RL Implementation
Issue -
State: open - Opened by FernandoRangel666 about 1 year ago
#307 - Implementing HER with Replay Buffer/Reverb
Issue -
State: open - Opened by lhendre over 1 year ago
- 1 comment
#306 - Masked actions in MCTS agent
Issue -
State: open - Opened by IngmarKI over 1 year ago
#305 - The program always executes behavior clone when running CQLLearner.
Issue -
State: open - Opened by jiangjiadi over 1 year ago
#304 - Add samples per second logging for `reverb_dataset.py`
Pull Request -
State: open - Opened by hartikainen over 1 year ago
#303 - Reference numbers for `reverb_benchmark.py`
Issue -
State: open - Opened by hartikainen over 1 year ago
- 2 comments
#302 - Inference server
Pull Request -
State: closed - Opened by samlobel over 1 year ago
- 1 comment
#301 - Is the last layer in distributional critic optimized (jax implementation)?
Issue -
State: open - Opened by Jogima-cyber over 1 year ago
- 1 comment
#300 - Reverb Replay Buffers + Vectorized/Batched Environments
Issue -
State: open - Opened by wbrenton over 1 year ago
- 1 comment
#299 - Library broken
Issue -
State: open - Opened by adiaconu11 over 1 year ago
- 1 comment
#298 - Use of tf.data.Dataset within tf.function
Issue -
State: closed - Opened by San-Holo over 1 year ago
- 1 comment
#297 - examples seem to be broken - examples/baselines/rl_continuous
Issue -
State: open - Opened by brian1985 over 1 year ago
- 2 comments
#296 - rewritten jnp.squeeze(self._value_layer(inputs), axis=-1)
Pull Request -
State: open - Opened by skywalker0803r over 1 year ago
- 1 comment
#295 - Error importing `matplotlib`
Issue -
State: open - Opened by cemlyn007 over 1 year ago
#294 - Missleading errors when using discrete action space with `CanonicalSpecWrapper`
Issue -
State: open - Opened by Whojo over 1 year ago
#293 - Converting Tensorflow Dataset to `iterator` does not sync well with client
Issue -
State: open - Opened by joeryjoery over 1 year ago
- 1 comment
#292 - D4PG jax agent computes n-step learning target in reverse?
Issue -
State: closed - Opened by joeryjoery over 1 year ago
- 5 comments
Labels: bug
#291 - DQN eval_epsilon overwrite with epsilon on 0.0
Issue -
State: open - Opened by tseyde over 1 year ago
#290 - Offline and Imitation Learning Examples seemingly do not work
Issue -
State: closed - Opened by EdanToledo over 1 year ago
- 1 comment
#289 - Sonnet issue with tf2
Issue -
State: open - Opened by suhani247 over 1 year ago
#288 - both Colab Notebooks give runtime errors
Issue -
State: closed - Opened by doesburg11 over 1 year ago
#287 - Support specifying fill behavior in frame_stacking
Pull Request -
State: open - Opened by ethanluoyc almost 2 years ago
#286 - OverflowError in _disable_insert_blocking when using samples_per_insert=None
Issue -
State: open - Opened by KaleabTessera almost 2 years ago
#285 - Avoid inlining large arrays in JaxInMemoryRandomSampleIterator
Issue -
State: open - Opened by ethanluoyc almost 2 years ago
#284 - MuZero agent in examples folder not present
Issue -
State: open - Opened by wcarvalho almost 2 years ago
- 1 comment
#283 - Question: Performance of multi-device prefetching
Issue -
State: open - Opened by EdanToledo almost 2 years ago
- 2 comments
#282 - run_mogmpo.py -- ValueError: Graph parent item 0 is not a Tensor;
Issue -
State: open - Opened by dyth almost 2 years ago
- 2 comments
#281 - Support JAX Array
Issue -
State: open - Opened by cemlyn007 almost 2 years ago
#280 - Quickstart notebook not working in Colab
Issue -
State: open - Opened by callumtilbury almost 2 years ago
#279 - InferenceServer Error
Issue -
State: open - Opened by kinalmehta almost 2 years ago
- 13 comments
#278 - Installing on Apple M1
Issue -
State: open - Opened by fazaghifari almost 2 years ago
- 4 comments
#277 - Bugs in the CRR code
Issue -
State: closed - Opened by qsa-fox almost 2 years ago
- 1 comment
#276 - Do you have NGU implementation?
Issue -
State: closed - Opened by GoingMyWay about 2 years ago
- 2 comments
#275 - Attribute error (no attributed CacherNode) when trying to run DistributedDQN
Issue -
State: open - Opened by SaundersJE97 about 2 years ago
#272 - Is it possible to run mompo for discrete and continuous action spaces?
Issue -
State: open - Opened by Nahid-Quader about 2 years ago
#271 - New Release
Issue -
State: open - Opened by cemlyn007 about 2 years ago
- 3 comments
Labels: bug
#270 - MPO temperature updates
Issue -
State: closed - Opened by henry-prior about 2 years ago
- 4 comments
Labels: question
#269 - Low SPS with `run_impala.py`
Issue -
State: closed - Opened by vwxyzjn about 2 years ago
- 7 comments
Labels: question
#268 - Reverb is not compatible with Windows
Issue -
State: closed - Opened by FinAminToastCrunch about 2 years ago
- 1 comment
#267 - Errors while running DistributedD4PG
Issue -
State: closed - Opened by kmukeshreddy about 2 years ago
- 33 comments
#266 - Changes in gym step and reset
Issue -
State: closed - Opened by rdevon about 2 years ago
- 3 comments
#265 - Regarding controlled runs for D4PG lp.launch
Issue -
State: closed - Opened by kmukeshreddy about 2 years ago
#264 - Basic SAC cartpole example fails: unexpected keyword argument 'minimum'
Issue -
State: closed - Opened by rdevon about 2 years ago
- 2 comments
#263 - Number of steps per second (Steps Per Second) for D4PG Agent
Issue -
State: closed - Opened by kmukeshreddy about 2 years ago
#262 - The Tutorial part should update
Issue -
State: closed - Opened by ruyikang about 2 years ago
- 3 comments
#261 - Add meltingpot MultiagentDictKeyWrapper support
Pull Request -
State: open - Opened by alan-cooney about 2 years ago
#260 - Fix the quickstart notebook
Pull Request -
State: closed - Opened by alan-cooney about 2 years ago
- 1 comment
#259 - Wrong recurrent state accessed in R2D2 Learner
Issue -
State: closed - Opened by ostap-viniavskyi about 2 years ago
- 1 comment
#258 - Problems with MBOP in offline examples
Issue -
State: open - Opened by ZhengyaoJiang over 2 years ago
#257 - Stupid question: Where do the 'objectives' go in the MOMPO model?
Issue -
State: open - Opened by MotorCityCobra over 2 years ago
#256 - run_experiment allow different seeded/wrapped environments for train and eval
Issue -
State: closed - Opened by Andrewzh112 over 2 years ago
- 2 comments
#255 - Regarding Seed for tf rl agents in acme
Issue -
State: open - Opened by kmukeshreddy over 2 years ago
- 3 comments
#254 - pip install dm-acme[jax] has problem
Issue -
State: closed - Opened by ruyikang over 2 years ago
- 2 comments
#253 - Regarding the papers "What Matters for Adversarial Imitation Learning?"
Issue -
State: closed - Opened by nuomizai over 2 years ago
- 2 comments
#252 - pip install error
Issue -
State: closed - Opened by lukaemon over 2 years ago
- 1 comment
#251 - Use typing.Mapping instead of collections.abc.Mapping
Pull Request -
State: open - Opened by ethanluoyc over 2 years ago
#250 - what is the helpers library
Issue -
State: closed - Opened by Mo379 over 2 years ago
- 2 comments
#249 - Fix policy loss gradient in TD3
Pull Request -
State: open - Opened by ethanluoyc over 2 years ago
- 1 comment
#248 - error running DQN example in distributed setting
Issue -
State: closed - Opened by kinalmehta over 2 years ago
- 1 comment
#247 - Cannot add extras to reverb adder
Issue -
State: closed - Opened by cop4587 over 2 years ago
#246 - Regarding Hyperparameter Search for acme tf agents (d4pg, dmpo)
Issue -
State: open - Opened by kmukeshreddy over 2 years ago
#245 - Qestion about updating the agent
Issue -
State: open - Opened by ZixuanLiu4869 over 2 years ago
- 5 comments
#244 - How to use in "production"?
Issue -
State: closed - Opened by sguysc over 2 years ago
- 6 comments
#243 - Understanding setting Reverb dataset parameters
Issue -
State: closed - Opened by ethanluoyc over 2 years ago
- 4 comments
#242 - dm-launchpad not available for Mac OS
Issue -
State: closed - Opened by kmukeshreddy over 2 years ago
- 1 comment
#241 - BUGFIX: Unpin tensorflow_datasets
Pull Request -
State: open - Opened by ethanluoyc over 2 years ago
- 3 comments
#240 - Issue when import acme
Issue -
State: closed - Opened by JiaojiaoYe1994 over 2 years ago
- 2 comments
#239 - Question about R2D2 loss, masking, and episode boundaries
Issue -
State: closed - Opened by wcarvalho over 2 years ago
- 2 comments
#238 - Add py.typed
Pull Request -
State: open - Opened by ethanluoyc over 2 years ago
- 1 comment
#237 - Improving snapshotting in JAX distributed experiments
Issue -
State: open - Opened by ethanluoyc over 2 years ago
- 8 comments
#236 - run_dqn demo fails with distributed training: ValueError: TrajectoryColumns cannot contain any None data references
Issue -
State: open - Opened by rdevon over 2 years ago
- 6 comments
#235 - Segmentation fault in using the new version of LocalLayout
Issue -
State: closed - Opened by ethanluoyc over 2 years ago
- 8 comments
#234 - RuntimeError: 'replay' nodes were not serializable
Issue -
State: closed - Opened by neardws over 2 years ago
- 6 comments
#232 - Log rewards statistics in SAC agents.
Pull Request -
State: open - Opened by wookayin over 2 years ago
- 2 comments
#231 - Use num_batch_dims=0 to deal with observations containing scalars
Pull Request -
State: open - Opened by wookayin over 2 years ago
- 1 comment
#229 - Release `wrappers` as PyPI package
Issue -
State: closed - Opened by kevinzakka over 2 years ago
- 6 comments
#226 - Regarding controlled runs for D4PG lp.launch
Issue -
State: closed - Opened by kmukeshreddy over 2 years ago
- 4 comments
#220 - Jitted Jax Environment Loop Support
Issue -
State: closed - Opened by djbyrne over 2 years ago
- 2 comments
#215 - Google Colab Acme tutorial datasets.make_reverb_dataset ValueError
Issue -
State: closed - Opened by DKevi over 2 years ago
- 4 comments
#182 - learner.step() error in tutorial.ipynb
Issue -
State: closed - Opened by kruthof almost 3 years ago
- 2 comments
#119 - Loading checkpoint does not work
Issue -
State: open - Opened by Idate96 over 3 years ago
- 6 comments
#106 - proper way to save and load
Issue -
State: open - Opened by philippGraf over 3 years ago
- 2 comments
#101 - Fix exception chaining order
Pull Request -
State: closed - Opened by cool-RR over 3 years ago
- 1 comment
Labels: cla: yes
#100 - Change bsuite dependency to point to PyPI package instead of Github repo
Pull Request -
State: closed - Opened by redfungus over 3 years ago
- 1 comment
Labels: cla: yes
#99 - Fix exception cause in video.py
Pull Request -
State: closed - Opened by cool-RR over 3 years ago
- 1 comment
Labels: cla: yes