Learning to play text-based adventure games with maximum entropy reinforcement learning
Text-based adventure games are a popular testbed for language based reinforcement
learning (RL). In previous work, deep Q-learning is most often used as the learning agent. Q …
learning (RL). In previous work, deep Q-learning is most often used as the learning agent. Q …
When Reasoning Meets Information Aggregation: A Case Study with Sports Narratives
Reasoning is most powerful when an LLM accurately aggregates relevant information. We
examine the critical role of information aggregation in reasoning by requiring the LLM to …
examine the critical role of information aggregation in reasoning by requiring the LLM to …