Arjun Gupta
Arjun Gupta
I have been trying to train an online agent on the environment FreewayNoFrameskip-v4. Because this gym environment is not deterministic, I seeded the environment. Specifically, in [atari_lib.py](https://github.com/google/dopamine/blob/master/dopamine/discrete_domains/atari_lib.py), I added -...
Was max-pooling of the last two frames performed in the pre-processing of the Atari datasets? The DQN Replay Dataset (An Optimistic Perspective on Offline Reinforcement Learning (ICML, 2020)) does max-pooling...
Hi! Thank you so much for making this work open source! I have a custom dataset (train/test) which I would like to use for training and testing. I was able...
I got the cross-entropy training to successfully train, now I am trying to get the self-critical sequence training portion of the training to work. The self-critical sequence training portion successfully...
While this repo supports MSCOCO and Flickr30k, if we were to replace all the data files (cocobu_att, cocobu_fc, cocotalk.json, cocotalk_label.h5, captions_val2014.json) with the equivalent for the Visual Genome dataset, would...
## Habitat-Sim version vx.x.x Habitat is under active development, and we advise users to restrict themselves to stable releases. Are you using the latest [release version](https://github.com/facebookresearch/habitat-sim/releases) of Habitat-Sim? Your question...
## Habitat-Sim version vx.x.x Habitat is under active development, and we advise users to restrict themselves to stable releases. Are you using the latest [release version](https://github.com/facebookresearch/habitat-sim/releases) of Habitat-Sim? Your question...
## Habitat-Lab and Habitat-Sim versions Habitat-Lab: master Habitat is under active development, and we advise users to restrict themselves to stable releases. Are you using the latest release versions of...
## Habitat-Lab and Habitat-Sim versions Habitat-Lab: master Habitat is under active development, and we advise users to restrict themselves to stable releases. Are you using the latest release versions of...
I have been trying to train an online agent on the environment FreewayNoFrameskip-v4. Because this gym environment is not deterministic, I seeded the environment. Specifically, in [atari_lib.py](https://github.com/google/dopamine/blob/master/dopamine/discrete_domains/atari_lib.py), I added -...