issues
search
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
Bootstrapped DQN
#513
prabhatnagarajan
opened
5 years ago
0
Define a softmax LSTM architecture
#512
oribarel
closed
5 years ago
1
Use chainer.grad in ACER
#511
muupan
closed
5 years ago
1
[WIP] Use chainer.as_variable
#510
muupan
opened
5 years ago
3
Improve the algorithm list on README
#509
muupan
closed
5 years ago
0
Fixes typo in docstring for AsyncEvaluator
#508
prabhatnagarajan
closed
5 years ago
0
Typo fix in Replay Buffer Docs
#507
prabhatnagarajan
closed
5 years ago
0
Splits Replay Buffers into separate files in a replay_buffers module
#506
prabhatnagarajan
closed
5 years ago
0
Adds backwards compatibility
#505
prabhatnagarajan
closed
5 years ago
0
Fix B006: Do not use mutable data structures for argument defaults.
#504
muupan
closed
5 years ago
0
Double IQN
#503
prabhatnagarajan
closed
5 years ago
4
Fix B007: Loop control variable not used within the loop body
#502
muupan
closed
5 years ago
0
Adds additional information to Grasping Example README
#501
prabhatnagarajan
closed
5 years ago
0
Port distributions into a distributions directory
#500
muupan
opened
5 years ago
0
Run slow tests by flexCI (perhaps manually)
#499
muupan
closed
4 years ago
0
Run example tests by flexCI
#498
muupan
opened
5 years ago
0
Adds training times for reproduced Mujoco results
#497
prabhatnagarajan
closed
5 years ago
3
Add links from algorithms/papers to examples in README
#496
muupan
closed
5 years ago
0
pytest==5.0.0 shows glitched output for tests/misc_tests/test_async.py
#495
muupan
opened
5 years ago
0
Upgrade to 0.7.0
#494
muupan
closed
5 years ago
0
Use Python 3.6 for ipynb
#493
toslunar
closed
5 years ago
0
Fix Travis error
#492
toslunar
closed
5 years ago
0
Monitor with ContinuingTimeLimit support
#491
keisuke-nakata
closed
5 years ago
0
Fixes incorrect comment.
#490
prabhatnagarajan
closed
5 years ago
0
Make `to_factorized_noisy` work with sequential links
#489
toslunar
closed
5 years ago
0
`to_factorized_noisy` wrongly modifies `chainerrl.links.Sequence`
#488
toslunar
closed
5 years ago
0
Rename examples directories
#487
keisuke-nakata
closed
5 years ago
2
Share persistent values among processes
#486
muupan
closed
5 years ago
5
Match EpisodicReplayBuffer.sample with ReplayBuffer.sample
#485
muupan
closed
5 years ago
0
Mismatch between EpisodicReplayBuffer.sample and ReplayBuffer.sample
#484
muupan
closed
5 years ago
0
Moves replay buffers to a directory
#483
prabhatnagarajan
closed
5 years ago
1
Port Replay Buffers into a ReplayBuffer Directory
#482
prabhatnagarajan
closed
5 years ago
0
Drops Chainer V4 Support
#481
prabhatnagarajan
closed
5 years ago
4
[WIP] DQfD
#480
ummavi
closed
4 years ago
0
Modifies permissions of tests to be executable directly
#479
prabhatnagarajan
closed
5 years ago
0
Add CI configs
#478
imos
closed
5 years ago
1
[WIP] IMPALA-style actor-learner parallelism for DQN variants
#477
muupan
opened
5 years ago
0
Add warning about numpy 1.16.0
#476
muupan
closed
5 years ago
1
Warn if numpy is 1.16.0
#475
muupan
closed
5 years ago
0
Adds reference to mujoco folder in the examples README
#474
prabhatnagarajan
closed
5 years ago
0
Drop python2 support
#473
muupan
closed
4 years ago
11
Split test_examples.sh
#472
muupan
closed
5 years ago
0
CI with type hinting
#471
muupan
opened
5 years ago
0
Adds IQN to the documentation.
#470
prabhatnagarajan
closed
5 years ago
0
Adds IQN Results to readme
#469
prabhatnagarajan
closed
5 years ago
0
Code to collect demonstrations from an agent.
#468
prabhatnagarajan
closed
5 years ago
1
Drop python2 support
#467
muupan
closed
4 years ago
1
Re-run Rainbow experiments
#466
muupan
closed
5 years ago
0
Apply `noisy_net_sigma` parameter
#465
keisuke-nakata
closed
5 years ago
1
[WIP] Code to collect demonstrations and perform behavioral cloning
#464
prabhatnagarajan
closed
5 years ago
0
Previous
Next