Playpen: An Environment for Exploring Learning From Dialogue Game Feedback

ACL ARR 2025 May Submission2929 Authors

Abstract:

Interaction between learner and feedback-giver has come into focus recently for post-training of Large Language Models (LLMs), through the use of reward models that judge the appropriateness of a model's response.
In this paper, we investigate whether Dialogue Games---goal-directed and rule-governed activities driven predominantly by verbal actions---can also serve as a source of feedback signals for learning.
We introduce Playpen, an environment for off- and online learning through Dialogue Game self-play, and investigate a representative set of post-training methods: supervised fine-tuning; direct alignment (DPO); and reinforcement learning with GRPO. We experiment with post-training a small LLM (Llama-3.1-8B-Instruct), evaluating performance on unseen instances of training games as well as unseen games, and on standard benchmarks. We find that imitation learning through SFT improves performance on unseen instances, but negatively impacts other skills, while interactive learning with GRPO shows balanced improvements without loss of skills. We release the framework and the baseline training setups to foster research in this promising new direction of ``learning in (synthetic) interaction''

Paper Type: Long

Research Area: Dialogue and Interactive Systems

Research Area Keywords: task-oriented,grounded dialog,evaluation and metrics

Contribution Types: NLP engineering experiment, Publicly available software and/or pre-trained models

Languages Studied: English

Submission Number: 2929