PyTorch implementation of papar Counting to Explore and Generalize in Text-based Games
{go, take} × {north, south, east, west, coin}
twcc_[mode]_level[level]_gamesize[#game]_step[max step]_seed[random seed]_[split]
, please check here for more details.coin_collector
branch
pip install https://github.com/microsoft/TextWorld/archive/refs/heads/coin_collector.zip
pip install gym_textworld/
.pip install tensorboardX
pip install nltk pytest
python -c "import nltk; nltk.download('punkt')"
tw-make.py <env_id>
to generate games corresponding to games defined in config files.
tw-make.py twcc_easy_level10_gamesize100_step50_seed9_train
.scripts/check_for_duplicates.py
to check duplicates between training and /test sets.python lstm_dqn_baseline/train_single_generate_agent.py -c lstm_dqn_baseline/config/
.python lstm_drqn_baseline/train_single_generate_agent.py -c lstm_drqn_baseline/config/
.