Scholarlink

Autonomous Agents trained with Reinforcement Learning (RL) must explore the effects of their actions in different environment states to learn optimal control policies  or build a model of such environment. Exploration may be impractical in complex environments, hence ways to prune the exploration space must be found. In this paper, we propose to augment an autonomous agent with a causal model of the core dynamics of its environment, learnt on a simplified version of it and then used as a “driving assistant” for larger or more complex environments. Experiments with different RL algorithms, in increasingly complex environments, and with different exploration strategies, show that learning such a model improves the agent behaviour.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Improving Reinforcement Learning-Based Autonomous Agents with Causal Models

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Giovanni Briglia,
  • Marco Lippi,
  • Stefano Mariani,
  • Franco Zambonelli

摘要

Autonomous Agents trained with Reinforcement Learning (RL) must explore the effects of their actions in different environment states to learn optimal control policies  or build a model of such environment. Exploration may be impractical in complex environments, hence ways to prune the exploration space must be found. In this paper, we propose to augment an autonomous agent with a causal model of the core dynamics of its environment, learnt on a simplified version of it and then used as a “driving assistant” for larger or more complex environments. Experiments with different RL algorithms, in increasingly complex environments, and with different exploration strategies, show that learning such a model improves the agent behaviour.