Papers by Renee Jia
Situated Dialogue Learning through Procedural Environment Generation (2022.acl-long)
Copied to clipboard
| Challenge: | a key hypothesis in the pursuit towards creating goal-driven natural language-based agents is interactivity and environment grounding is critical for effective language learning. |
| Approach: | They augment LIGHT by learning to procedurally generate additional novel textual worlds and quests to create a curriculum of steadily increasing difficulty for training agents. |
| Outcome: | The authors augment LIGHT by learning to procedurally generate additional novel textual worlds and quests to create a curriculum of increasing difficulty for training agents to achieve such goals. |