NLPGym -- A toolkit for evaluating RL agents on Natural Language Processing Tasks
This toolkit addresses a gap for NLP researchers by enabling consistent benchmarking of RL agents on standard tasks, though it is incremental as it adapts existing RL environment concepts to NLP.
The authors tackled the lack of simulated textual environments for applying reinforcement learning (RL) to natural language processing (NLP) tasks by releasing NLPGym, an open-source toolkit that provides interactive environments for tasks like sequence tagging and question answering, and they presented experimental results for 6 tasks as baselines.
Reinforcement learning (RL) has recently shown impressive performance in complex game AI and robotics tasks. To a large extent, this is thanks to the availability of simulated environments such as OpenAI Gym, Atari Learning Environment, or Malmo which allow agents to learn complex tasks through interaction with virtual environments. While RL is also increasingly applied to natural language processing (NLP), there are no simulated textual environments available for researchers to apply and consistently benchmark RL on NLP tasks. With the work reported here, we therefore release NLPGym, an open-source Python toolkit that provides interactive textual environments for standard NLP tasks such as sequence tagging, multi-label classification, and question answering. We also present experimental results for 6 tasks using different RL algorithms which serve as baselines for further research. The toolkit is published at https://github.com/rajcscw/nlp-gym