WordCraft: An Environment for Benchmarking Commonsense Agents
arXiv:2007.09185
Abstract
The ability to quickly solve a wide range of real-world tasks requires a commonsense understanding of the world. Yet, how to best extract such knowledge from natural language corpora and integrate it with reinforcement learning (RL) agents remains an open challenge. This is partly due to the lack of lightweight simulation environments that sufficiently reflect the semantics of the real world and provide knowledge sources grounded with respect to observations in an RL environment. To better enable research on agents making use of commonsense knowledge, we propose WordCraft, an RL environment based on Little Alchemy 2. This lightweight environment is fast to run and built upon entities and relations inspired by real-world semantics. We evaluate several representation learning methods on this new benchmark and propose a new method for integrating knowledge graphs with an RL agent.
References in corpus (14)
- A Review of Relational Machine Learning for Knowledge Graphs
- Dota 2 with Large Scale Deep Reinforcement Learning
- ConceptNet 5.5: An Open Multilingual Graph of General Knowledge
- IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
- Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning
- TextWorld: A Learning Environment for Text-based Games
- BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning
- Learning Dynamic Belief Graphs to Generalize on Text-Based Games
- Human Instruction-Following with Deep Reinforcement Learning via Transfer-Learning from Text
- TorchBeast: A PyTorch Platform for Distributed RL
- Unnatural Language Processing: Bridging the Gap Between Synthetic and Natural Language Data
- What can you do with a rock? Affordance extraction via word embeddings
- Enhancing Text-based Reinforcement Learning Agents with Commonsense Knowledge
- Building Dynamic Knowledge Graphs from Text-based Games