Pinned Repositories
Action-Eliminating-DQN
A DRL agent that learns to eliminate actions in order to solve text-based games with large action spaces: DQN tweaks for TBG + Zork framework is provided.
OpenSeq2Seq
Multi-GPU sequence to sequence learning
quantized.pytorch
sockeye
Sequence-to-sequence framework with a focus on Neural Machine Translation based on Apache MXNet
tensor2tensor
A library for generalized sequence to sequence models
tensorflow
Computation using data flow graphs for scalable machine learning
text-world-player
Framework and model code for the paper "Language Understanding for Text-based Games using Deep Reinforcement Learning", EMNLP 2015
tmp
utils.pytorch
Utilities for Pytorch
zork
The DUNGEON (Zork I) source - This code was slightly modified to create an emulator environment for the AE-DQN agent
matanhs's Repositories
matanhs/Action-Eliminating-DQN
A DRL agent that learns to eliminate actions in order to solve text-based games with large action spaces: DQN tweaks for TBG + Zork framework is provided.
matanhs/quantized.pytorch
matanhs/OpenSeq2Seq
Multi-GPU sequence to sequence learning
matanhs/sockeye
Sequence-to-sequence framework with a focus on Neural Machine Translation based on Apache MXNet
matanhs/tensor2tensor
A library for generalized sequence to sequence models
matanhs/tensorflow
Computation using data flow graphs for scalable machine learning
matanhs/text-world-player
Framework and model code for the paper "Language Understanding for Text-based Games using Deep Reinforcement Learning", EMNLP 2015
matanhs/utils.pytorch
Utilities for Pytorch
matanhs/zork
The DUNGEON (Zork I) source - This code was slightly modified to create an emulator environment for the AE-DQN agent
matanhs/tmp