Ashutosh-Adhikari

Resolve PEP8 Issues

1

Resolve design recipe issues like import order and passing kwargs. Refer PEP8.

Add Prioritized Experience Replay for Rainbow implementation

3

Should we work upon adding Prioritized Experience Replay ?

Add PER

3

Hi, The reference code for PER additions : https://github.com/Kaixhin/Rainbow.git. It is segment tree based implementation of PER.

Training plot for boxing giving values much greater than Evaluation

2

While training, the scale of summed clipped rewards that an agent gets is much higher than what it gets for boxing and much lower for games like qbert and spaceinvaders....

Testing a trained model throws error

1

We don't need to search for a snapshot when using the flag --trained-model.

This PR addresses the issue #8 .

DGCNN in PyTorch

2

Hi, I see there is a code for PyTorch written in the repo. Is it in working condition.

Fix tokenizer for reuters dataset

1

Need to remove a few characters ( like `?`, `!` ) from sentences. In other words, add a few relevant delimiters.

Generate vocabs while creating data

1

Hello, I face an issue while training on the baselines repo if the vocabularies aren't generated. I see there is `--generate_vocabularies` flag in the baselines' repository, but is there a...