Experience enrichment based task independent reward model

TL;DR

This paper introduces a task-independent implicit reward model for reinforcement learning that derives rewards from deviations in agents' experiences, aiming to better reflect real-world complex interactions.

Contribution

The paper proposes a novel implicit reward model that is task-independent and based on experience deviations, differing from traditional manually defined rewards.

Findings

The implicit reward model effectively captures complex interactions.

It improves the generality of reinforcement learning approaches.

The model is adaptable to various environments.

Abstract

For most reinforcement learning approaches, the learning is performed by maximizing an accumulative reward that is expectedly and manually defined for specific tasks. However, in real world, rewards are emergent phenomena from the complex interactions between agents and environments. In this paper, we propose an implicit generic reward model for reinforcement learning. Unlike those rewards that are manually defined for specific tasks, such implicit reward is task independent. It only comes from the deviation from the agents' previous experiences.