XiaoxiaoGuo / rcdqn
This repository contains the source code of the EMNLP 2020 paper Interactive Fiction Game Playing as Multi-Paragraph Reading Comprehension with Reinforcement Learning.
☆20Updated 4 years ago
Alternatives and similar repositories for rcdqn:
Users that are interested in rcdqn are comparing it to the libraries listed below
- [ICLR 2022 Spotlight] Multi-Stage Episodic Control for Strategic Exploration in Text Games☆14Updated 3 years ago
- Goal driven language generation using knowledge graph A2C agents☆60Updated 5 years ago
- Experiment code for the ICLR 2020 paper "RTFM: Generalising to New Environment Dynamics via Reading".☆38Updated 3 years ago
- ☆36Updated 9 months ago
- ☆20Updated 3 years ago
- Learning with latent language☆51Updated 4 years ago
- Template-DQN and DRRN agent implementations☆22Updated last year
- ☆32Updated 3 years ago
- This framework provides out-of-the-box implementations of Referential Games variants in order to study the emergence of artificial langua…☆22Updated last month
- Super fast implementations of common benchmark text world games☆47Updated last month
- Graph-based Deep Q Network for Web Navigation☆47Updated 5 years ago
- Question Answering with Interactive Text (QAit), code for EMNLP 2019 paper "Interactive Language Learning by Question Answering"☆44Updated 5 years ago
- A2C for GVG-AI☆21Updated 6 years ago
- The multi-modal sequence to sequence baseline neural models used in the Grounded SCAN paper.☆16Updated 4 years ago
- ☆84Updated 5 years ago
- BabyAI++: Towards Grounded language Learning beyond Memorization, ICLR BeTR-RL 2020☆25Updated 4 years ago
- This repository contains the code used for Ordered Memory paper☆30Updated 5 years ago
- The official repository for our paper "The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization".☆33Updated 3 years ago
- Automatically Composing Representation Transformations as a Means for Generalization☆24Updated 5 years ago
- Tensor product decomposition network☆19Updated 4 years ago
- ReaSCAN is a synthetic navigation task that requires models to reason about surroundings over syntactically difficult languages. (NeurIPS…☆20Updated 3 years ago
- Solving reinforcement learning tasks which require language and vision☆32Updated 2 years ago
- Finding Generalizable Evidence by Learning to Convince Q&A Models☆25Updated 2 years ago
- Measuring compositionality in representation learning☆73Updated 5 years ago
- Annotated bibliographies.☆40Updated 5 years ago
- ☆13Updated 6 years ago
- NAIL is an agent that plays text-based interactive fiction games.☆46Updated last year
- Reproducing the reinforcement learning models used in "Emergence of Linguistic Communication from Referential Games with Symbolic and Pix…☆12Updated 6 years ago
- Official code for "Can Wikipedia Help Offline Reinforcement Learning?" by Machel Reid, Yutaro Yamada and Shixiang Shane Gu☆104Updated 2 years ago
- On the pitfalls of measuring emergent communication☆34Updated 6 years ago