pfrl

pfrl copied to clipboard

[Feature Request/Proposal] use MLFlow option or best practice of experiments management

1

Thank you for the excellent RL library. PFRL makes my life so much easy. As the management of the experiment becomes complicated, I have tried PFRL with MLFlow. And I'm...

Chachay

Enable auto assign for a PR that was a draft PR but now is marked ready for review

1

It seems not enabled right now, and manually rerunning the job has no effect. https://github.com/pfnet/pfrl/pull/98/checks?check_run_id=1451297003 > Skips the process to add reviewers/assignees since PR type is draft

muupan

# Abstract: `ActionValue` classes and backward hooks cause an error when used together. # Details Several pre-defined models in PFRL, such as `FCQuadraticStateQFunction`, return `ActionValue` from its forward function. However,...

keisukefukuda

prabhatnagarajan

prabhatnagarajan

Some tests still have `@pytest.mark.skip` annotation from pre-migration. These tests should be updated or removed.

prabhatnagarajan

Memory leak (?) when run without a GPU

2

Disclaimer: I am not completely sure if this is a bug of PFRL. When I ran SAC, and TD3 on my university's cluster without a GPU, I observed that memory...

tadashiK

The score of `train_dqn_gym.py` with `--actor-learner` is lower than the baseline score.

1

It seems that the score of `train_dqn_gym.py` with `--actor-learner` is lower than the baseline score. the result of `train_dqn_gym.py` with `--actor-learner` ``` $python train_dqn_gym.py --env CartPole-v0 --gpu -1 --actor-learner $cat...

shu65

Double IQN

3

Add Double IQN with a double update (as in ChainerRL - https://github.com/chainer/chainerrl/blob/master/chainerrl/agents/double_iqn.py)

prabhatnagarajan

Timeout occurs occasionally.

muupan