chainer chainerrl issues

chainer / chainerrl

ChainerRL is a deep reinforcement learning library built on top of Chainer.

MIT License

1.18k stars 224 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

GPU does not work in train_a3c.py file

#563 Ujwal2910 closed 5 years ago
3
guide on how to use LSTM version of DDPG on gym environments

#562 junhuang-ifast closed 5 years ago
10
Fixes Rainbow Score to use correct Reporting Protocol

#561 prabhatnagarajan closed 5 years ago
0
Fixes Rainbow Score to use correct Reporting Protocol

#560 prabhatnagarajan closed 5 years ago
1
Report Correct Evaluations for Rainbow

#559 prabhatnagarajan closed 5 years ago
1
Pass env_id to replay_buffer methods to fix batch training

#558 ummavi closed 5 years ago
6
Bug in Soft Actor Critic's batch_observe_and_train

#557 ummavi closed 5 years ago
2
Add documentation for Q-functions and some missing details in docstrings

#556 marioyc closed 5 years ago
4
TestStatelessRecurrentSequential.test_n_step_forward_gpu is flaky

#555 muupan opened 5 years ago
0
decrease amount of decimal digits required to 4

#554 marioyc closed 5 years ago
2
Run A3C example and collect results

#553 prabhatnagarajan closed 5 years ago
0
Corrects Scores in Examples

#552 prabhatnagarajan closed 5 years ago
2
Add trained models

#551 prabhatnagarajan closed 3 years ago
2
Increase flexCI's time limit to 20min

#550 muupan closed 5 years ago
2
Improves formatting of IQN training times

#549 prabhatnagarajan closed 5 years ago
6
Update train_a3c.py

#548 xinyuewang1 closed 5 years ago
2
Update train_a3c.py

#547 xinyuewang1 closed 5 years ago
2
Rainbow Scores

#546 prabhatnagarajan closed 5 years ago
14
TestSquashedGaussianDistribution.test_sample_with_log_prob is flaky

#545 muupan closed 5 years ago
1
Improves formatting of IQN Training times

#544 prabhatnagarajan closed 5 years ago
2
Adds List of Batch Agents to the README

#543 prabhatnagarajan closed 5 years ago
2
TestCastObservation.test_cast_observation is flaky

#542 muupan opened 5 years ago
0
fix function call

#541 marioyc closed 5 years ago
6
Improve parameter distributions used in TestGaussianDistribution

#540 muupan closed 5 years ago
4
Use get_device_from_id since get_device is deprecated

#539 muupan closed 5 years ago
0
Avoid cupy.zeros_like with numpy.ndrray

#538 muupan closed 5 years ago
0
Use cupyx.scatter_add instead of cupy.scatter_add

#537 muupan closed 5 years ago
2
Use Link.cleargrads instead of Link.zerograds in REINFORCE

#536 muupan closed 5 years ago
4
SARSA raises an error with GPU: ValueError: Unsupported dtype object

#535 muupan closed 5 years ago
0
Fix ValueError in SARSA with GPU

#534 muupan closed 5 years ago
6
Make test_monitor.py work on flexCI

#533 muupan closed 5 years ago
8
chainerrl/tests/wrappers_tests/test_monitor.py fails on flexCI

#532 muupan closed 5 years ago
0
Fix import error when chainer==7.0.0b3

#531 muupan closed 5 years ago
0
Path to the `n_step_lstm` module has changed in chainer==7.0.0b3

#530 muupan closed 5 years ago
0
Add a deterministic mode to IQN for stable tests

#529 muupan closed 5 years ago
4
Fix a bug in `batch_recurrent_experiences` regarding next_action

#528 muupan closed 5 years ago
0
Bug in `batch_recurrent_experiences` regarding next_action

#527 muupan closed 5 years ago
0
Remove a tailing space of DoubleIQN

#526 muupan closed 5 years ago
0
Adds checkpoint frequencies for serial and batch Agents.

#525 prabhatnagarajan closed 5 years ago
4
Add policy loss to TD3's logged statistics

#524 ummavi closed 5 years ago
0
Unable to load two models in the same script

#523 russelltankl closed 5 years ago
2
IQN's slow tests are unstable

#522 muupan closed 5 years ago
0
Fixes a comment in PPO example

#521 prabhatnagarajan closed 5 years ago
0
Specify ubuntu 16.04 for Travis CI and modify a dependency accordingly

#520 muupan closed 5 years ago
0
Travis CI failure with ubuntu 16.04

#519 muupan closed 5 years ago
0
Prioritized Double IQN

#518 prabhatnagarajan closed 5 years ago
10
Adds demonstration collection to experiments docs

#517 prabhatnagarajan closed 5 years ago
0
Adds policies to the documentation

#516 prabhatnagarajan closed 5 years ago
1
Fixes syntax errors in ReplayBuffer docs.

#515 prabhatnagarajan closed 5 years ago
0
Add Explorers to Documentation

#514 prabhatnagarajan closed 5 years ago
0

Previous Next