chainer/chainerrl

Issues

• Regarding the output of DQN

  #612 opened 3 years ago by KitanoFumiya
  1

• Add trained models

  #551 opened 3 years ago by prabhatnagarajan
  2

• AdditiveGaussian Overflow

  #603 opened 4 years ago by mcmips
  0

• What's does the columns in scores.txt mean?

  #604 opened 4 years ago by Nina-9519
  1

• What do 'agent.save' mean??

  #588 opened 4 years ago by KitanoFumiya
  5

• Tensorboard support

  #597 opened 4 years ago by Ujwal2910
  2

• Question: How to create a model which takes two inputs?

  #598 opened 4 years ago by HadiSDev
  1

• (How to) Provide a random agent for evaluation

  #599 opened 4 years ago by Pit-Storm
  1

• SARSA missing on GitHub page and API description is incorrect?

  #600 opened 4 years ago by MieszkoFerens
  3

• RuntimeError: CUDA environment is not correctly set up

  #602 opened 4 years ago by THSWind
  3

• Downloading pretrained DQN models gives error: HTTP Error 403: Forbidden

  #601 opened 4 years ago by aguamentiPatronum
  2

• Can I get the distortion data in MujoCo?

  #594 opened 4 years ago by KitanoFumiya
  0

• I want to know delta in TRPO

  #593 opened 4 years ago by KitanoFumiya
  0

• Segmentation fault in Docker after importing chainerrl

  #589 opened 4 years ago by russelltankl
  2

• Question about quantile huber loss function in IQN

  #590 opened 4 years ago by ShogoAkiyama
  1

• Saving models at timestamps

  #586 opened 4 years ago by Ujwal2910
  4

• Drop python2 support

  #467 opened 4 years ago by muupan
  1

• Run slow tests by flexCI (perhaps manually)

  #499 opened 4 years ago by muupan
  0

• Run A3C example and collect results

  #553 opened 5 years ago by prabhatnagarajan
  0

• Report Correct Evaluations for Rainbow

  #559 opened 5 years ago by prabhatnagarajan
  1

• Bug in Soft Actor Critic's batch_observe_and_train

  #557 opened 5 years ago by ummavi
  2

• TestTrainAgentAsync.test is flaky

  #578 opened 5 years ago by muupan
  0

• Fully Parameterized Quantile Function for Distributional Reinforcement Learning

  #573 opened 5 years ago by muupan
  0

• Async training does not work with macOS and Python 3.8

  #572 opened 5 years ago by muupan
  0

• Compatibility with OpenAI Gym's VectorEnv

  #571 opened 5 years ago by muupan
  0

• KeyError-249

  #566 opened 5 years ago by Ujwal2910
  1

• GPU does not work in train_a3c.py file

  #563 opened 5 years ago by Ujwal2910
  3

• guide on how to use LSTM version of DDPG on gym environments

  #562 opened 5 years ago by junhuang-ifast
  10

• Re-run Rainbow experiments

  #466 opened 5 years ago by muupan
  0

• TestStatelessRecurrentSequential.test_n_step_forward_gpu is flaky

  #555 opened 5 years ago by muupan
  0

• IQN's slow tests are unstable

  #522 opened 5 years ago by muupan
  0

• TestSquashedGaussianDistribution.test_sample_with_log_prob is flaky

  #545 opened 5 years ago by muupan
  1

• SARSA raises an error with GPU: ValueError: Unsupported dtype object

  #535 opened 5 years ago by muupan
  0

• TestCastObservation.test_cast_observation is flaky

  #542 opened 5 years ago by muupan
  0

• Run example tests by flexCI

  #498 opened 5 years ago by muupan
  0

• chainerrl/tests/wrappers_tests/test_monitor.py fails on flexCI

  #532 opened 5 years ago by muupan
  0

• Path to the `n_step_lstm` module has changed in chainer==7.0.0b3

  #530 opened 5 years ago by muupan
  0

• Bug in `batch_recurrent_experiences` regarding next_action

  #527 opened 5 years ago by muupan
  0

• Port distributions into a distributions directory

  #500 opened 5 years ago by muupan
  0

• Unable to load two models in the same script

  #523 opened 5 years ago by russelltankl
  2

• Add links from algorithms/papers to examples in README

  #496 opened 5 years ago by muupan
  0

• Travis CI failure with ubuntu 16.04

  #519 opened 5 years ago by muupan
  0

• Define a softmax LSTM architecture

  #512 opened 5 years ago by oribarel
  1

• Bootstrapped DQN

  #513 opened 5 years ago by prabhatnagarajan
  0

• Port Replay Buffers into a ReplayBuffer Directory

  #482 opened 5 years ago by prabhatnagarajan
  0

• pytest==5.0.0 shows glitched output for tests/misc_tests/test_async.py

  #495 opened 5 years ago by muupan
  0

• `to_factorized_noisy` wrongly modifies `chainerrl.links.Sequence`

  #488 opened 5 years ago by toslunar
  0

• Mismatch between EpisodicReplayBuffer.sample and ReplayBuffer.sample

  #484 opened 5 years ago by muupan
  0

• Warn if numpy is 1.16.0

  #475 opened 5 years ago by muupan
  0

• CI with type hinting

  #471 opened 5 years ago by muupan
  0