Giters
yandexdataschool
/
Practical_RL
A course in reinforcement learning in the wild
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
5787
Watchers:
210
Issues:
186
Forks:
1676
yandexdataschool/Practical_RL Issues
Remove Theano/Lasagne support
Closed
3 years ago
Ensure that week4/dqn_breakout is not broken
Closed
3 years ago
Comments count
1
week3/qlearning is difficult to pass for wrong reasons
Closed
4 years ago
Comments count
2
It should be clear why we have multiple Dockerfiles
Closed
4 years ago
Comments count
2
Multiple packages are missing in Docker image
Closed
4 years ago
week07_seq2seq/main_dataset.txt has duplicate lines
Closed
4 years ago
week10/seminar_mcts: rollout() should return immediate_reward if is_done
Closed
4 years ago
week10/seminar_mcts: discards value for expanded child
Closed
4 years ago
Better Docker instructions
Updated
4 years ago
Comments count
1
coursera/week6/seq2seq/basic_model_tf.py hangs with TF 1.14.0
Updated
4 years ago
Comments count
3
Bandit assignment is too unstable
Updated
4 years ago
Comments count
1
Solutions to week2/seminar often calculate max incorrectly
Closed
4 years ago
Comments count
1
Outdated explicit dependencies in week04_[recap]_deep_learning/seminar_pytorch.ipynb
Closed
4 years ago
Comments count
1
week04_approx_rl/seminar_pytorch.ipynb is confusing at "avoid using nonlinearities like sigmoid & tanh"
Closed
4 years ago
Replace all atari_util.py variations with an import from stable_baselines.common.atari_wrappers
Updated
4 years ago
Put all code that we reuse across weeks in an importable library
Updated
4 years ago
Comments count
1
Incorrect observation_shape in week04/homework_tf?
Closed
4 years ago
Comments count
1
coursera/week5/policy-based quiz/q2 does not have a correct answer
Closed
4 years ago
Comments count
1
coursera/week6/mcts quiz/q1 is confusing
Closed
4 years ago
Comments count
1
coursera/week6/mcts quiz/q2 is confusing
Closed
4 years ago
Comments count
1
Port changes from master to coursera
Closed
4 years ago
Comments count
1
Collect FAQ for Coursera
Closed
4 years ago
Comments count
1
Issue with reward scaling in week08/practice?
Closed
4 years ago
Comments count
2
Use `if 'google.colab' in sys.modules` instead of `# uncomment this if you Colab`
Closed
4 years ago
Comments count
1
[week06/reinforce_pytorch] Mistake in objective function formula
Closed
4 years ago
More verbose grader feedback than "game over"
Closed
4 years ago
Comments count
1
pytorch version of coursera notebook is outdated
Closed
4 years ago
Comments count
2
Image scaling in A3C (coursera)
Closed
5 years ago
Comments count
3
MCTS seminar still refers to render(close=True)
Closed
5 years ago
week04_approx_rl/homework_tf.ipynb calls print() without parentheses
Closed
5 years ago
(Probably) mistake in PPO policy loss formula
Closed
5 years ago
Comments count
1
Outdated instructions for setting up Coursera environment?
Closed
5 years ago
Comments count
1
Implement grader for coursera/week6/seq2seq
Closed
5 years ago
Comments count
2
_observation is deprecated in ObservationWrapper
Closed
5 years ago
week2/practice_vi: MDP test is nondeterministic
Closed
5 years ago
Default Tensorboard port should not be 6000
Closed
5 years ago
Comments count
2
Bug in MDP data in week02_value_based/seminar_vi.ipynb
Closed
5 years ago
Comments count
2
week07/basic_model_tf: states_seq is computed but not returned
Closed
5 years ago
Coursera environment is unsuitable for lengthy training
Closed
5 years ago
Comments count
1
Wrapper interface is broken in a recent Gym version
Closed
5 years ago
Comments count
1
Mistake in week02_value_based/seminar_vi?
Closed
5 years ago
Comments count
1
coursera/week6/mcts quiz/q4 is confusing
Closed
5 years ago
Comments count
1
coursera/week2/optimality quiz is confusing
Closed
5 years ago
Comments count
2
coursera/week4/quiz2/q2 is ambiguous
Closed
5 years ago
Comments count
2
s/spring19/master/g
Closed
5 years ago
How can i access the tensorboard at port 6000 ?
Closed
5 years ago
Comments count
4
coursera/week5/policy quiz/q5 should have answer options in proper LaTeX
Closed
5 years ago
Comments count
3
week1/cem criteria for passing are unclear
Closed
5 years ago
Comments count
2
Test readme-md-generator on our repo
Updated
5 years ago
seminar_TRPO_tensorflow wrong formulae?
Closed
5 years ago
Comments count
1
Previous
Next