In an LLM-generated text survival game, a GPT-4o agent was reported to survive better and score more ethically than NEAT and SVI Bayesian agents, but the evaluation is circular because GPT-4o labels its own behavior.
Playing Text-Based Games with Common Sense
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Text based games are simulations in which an agent interacts with the world purely through natural language. They typically consist of a number of puzzles interspersed with interactions with common everyday objects and locations. Deep reinforcement learning agents can learn to solve these puzzles. However, the everyday interactions with the environment, while trivial for human players, present as additional puzzles to agents. We explore two techniques for incorporating commonsense knowledge into agents. Inferring possibly hidden aspects of the world state with either a commonsense inference model COMET, or a language model BERT. Biasing an agents exploration according to common patterns recognized by a language model. We test our technique in the 9to05 game, which is an extreme version of a text based game that requires numerous interactions with common, everyday objects in common, everyday scenarios. We conclude that agents that augment their beliefs about the world state with commonsense inferences are more robust to observational errors and omissions of common elements from text descriptions.
fields
cs.AI 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
The Odyssey of the Fittest: Can Agents Survive and Still Be Good?
In an LLM-generated text survival game, a GPT-4o agent was reported to survive better and score more ethically than NEAT and SVI Bayesian agents, but the evaluation is circular because GPT-4o labels its own behavior.