An Analysis of Deep Reinforcement Learning Agents for Text-based Games
This work addresses the problem of evaluating and designing agents for text-based games, but it appears incremental as it focuses on analysis and categorization rather than novel breakthroughs.
The authors tackled the challenge of balancing efficiency and performance in deep reinforcement learning agents for text-based games by constructing a standardized agent without hand-crafted rules and categorizing evaluation types, but no concrete results or numbers were reported.
Text-based games(TBG) are complex environments which allow users or computer agents to make textual interactions and achieve game goals.In TBG agent design and training process, balancing the efficiency and performance of the agent models is a major challenge. Finding TBG agent deep learning modules' performance in standardized environments, and testing their performance among different evaluation types is also important for TBG agent research. We constructed a standardized TBG agent with no hand-crafted rules, formally categorized TBG evaluation types, and analyzed selected methods in our environment.