Playpen: An Environment for Exploring Learning Through Conversational Interaction

• URL: http://arxiv.org/abs/2504.08590v1
• Date: Fri, 11 Apr 2025 14:49:33 GMT
• Title: Playpen: An Environment for Exploring Learning Through Conversational Interaction
• Authors: Nicola Horst, Davide Mazzaccara, Antonia Schmidt, Michael Sullivan, Filippo Momentè, Luca Franceschetti, Philipp Sadler, Sherzod Hakimov, Alberto Testoni, Raffaella Bernardi, Raquel Fernández, Alexander Koller, Oliver Lemon, David Schlangen, Mario Giulianelli, Alessandro Suglia,
• Abstract summary: We look at what extent synthetic interaction in what we call Dialogue Games can provide a learning signal.<n>We investigate the effects of supervised fine-tuning on this data.<n>We release the framework and the baseline training setups in the hope that this can foster research in this promising new direction.
• Score: 81.67330926729015
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Are we running out of learning signal? Predicting the next word in an existing text has turned out to be a powerful signal, at least at scale. But there are signs that we are running out of this resource. In recent months, interaction between learner and feedback-giver has come into focus, both for "alignment" (with a reward model judging the quality of instruction following attempts) and for improving "reasoning" (process- and outcome-based verifiers judging reasoning steps). In this paper, we explore to what extent synthetic interaction in what we call Dialogue Games -- goal-directed and rule-governed activities driven predominantly by verbal actions -- can provide a learning signal, and how this signal can be used. We introduce an environment for producing such interaction data (with the help of a Large Language Model as counterpart to the learner model), both offline and online. We investigate the effects of supervised fine-tuning on this data, as well as reinforcement learning setups such as DPO, and GRPO; showing that all of these approaches achieve some improvements in in-domain games, but only GRPO demonstrates the ability to generalise to out-of-domain games as well as retain competitive performance in reference-based tasks. We release the framework and the baseline training setups in the hope that this can foster research in this promising new direction.

Related papers

• Learning Manipulation by Predicting Interaction [85.57297574510507]
  We propose a general pre-training pipeline that learns Manipulation by Predicting the Interaction. The experimental results demonstrate that MPI exhibits remarkable improvement by 10% to 64% compared with previous state-of-the-art in real-world robot platforms.
  arXiv  Detail & Related papers  (2024-06-01T13:28:31Z)
• clembench-2024: A Challenging, Dynamic, Complementary, Multilingual Benchmark and Underlying Flexible Framework for LLMs as Multi-Action Agents [19.989503513817095]
  Large Language Models can be prompted to "self-play" conversational games that probe certain capabilities. We take one of the proposed frameworks for setting up such game-play environments, and test its usefulness as an evaluation instrument.
  arXiv  Detail & Related papers  (2024-05-31T14:43:31Z)
• Yes, this Way! Learning to Ground Referring Expressions into Actions with Intra-episodic Feedback from Supportive Teachers [15.211628096103475]
  We present an initial study that evaluates intra-episodic feedback given in a collaborative setting. Our results show that intra-episodic feedback allows the follower to generalize on aspects of scene complexity.
  arXiv  Detail & Related papers  (2023-05-22T10:01:15Z)
• RLIP: Relational Language-Image Pre-training for Human-Object Interaction Detection [32.20132357830726]
  Language-Image Pre-training (LIPR) is a strategy for contrastive pre-training that leverages both entity and relation descriptions. We show the benefits of these contributions, collectively termed RLIP-ParSe, for improved zero-shot, few-shot and fine-tuning HOI detection as well as increased robustness from noisy annotations.
  arXiv  Detail & Related papers  (2022-09-05T07:50:54Z)
• End-to-End Active Speaker Detection [58.7097258722291]
  We propose an end-to-end training network where feature learning and contextual predictions are jointly learned. We also introduce intertemporal graph neural network (iGNN) blocks, which split the message passing according to the main sources of context in the ASD problem. Experiments show that the aggregated features from the iGNN blocks are more suitable for ASD, resulting in state-of-the art performance.
  arXiv  Detail & Related papers  (2022-03-27T08:55:28Z)
• PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning [102.36450942613091]
  We propose an inverse reinforcement learning algorithm, called emphinverse temporal difference learning (ITD) We show how to seamlessly integrate ITD with learning from online environment interactions, arriving at a novel algorithm for reinforcement learning with demonstrations, called $Psi Phi$-learning.
  arXiv  Detail & Related papers  (2021-02-24T21:12:09Z)
• A Graph-based Interactive Reasoning for Human-Object Interaction Detection [71.50535113279551]
  We present a novel graph-based interactive reasoning model called Interactive Graph (abbr. in-Graph) to infer HOIs. We construct a new framework to assemble in-Graph models for detecting HOIs, namely in-GraphNet. Our framework is end-to-end trainable and free from costly annotations like human pose.
  arXiv  Detail & Related papers  (2020-07-14T09:29:03Z)
• On the interaction between supervision and self-play in emergent communication [82.290338507106]
  We investigate the relationship between two categories of learning signals with the ultimate goal of improving sample efficiency. We find that first training agents via supervised learning on human data followed by self-play outperforms the converse.
  arXiv  Detail & Related papers  (2020-02-04T02:35:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.