arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.07562cs.LGcs.MA
收藏

多智能体竞争中的安全适应

Safe adaptation in multiagent competition

Massachusetts Institute of Technology(麻省理工学院)

Macheng Shen, Jonathan P. How

摘要:

实现适应不断变化的环境的能力是构建在复杂场景中安全运行的完全自主机器人的关键一步。在多智能体竞争的情况下,智能体可能要适应新的对手与以前看不见的行为,从自我智能体和对手之间的互动经验学习。然而,这种适应容易受到对手的利用。当自我智能体更新自己的行为以利用对手时,由于过度拟合这个特定对手的行为,它自己的行为可能变得更容易利用。为了克服这一困难,我们开发了一种安全的适应方法,在该方法中,自我代理是针对正则化的对手模型进行训练的,这有效地避免了过拟合,从而提高了自我代理策略的鲁棒性。我们评估了我们的方法在Mujoco域与两个竞争的代理。实验结果表明,我们的方法有效地实现了适应特定的对手,自我代理与其他可能的对手剥削保持低利用率。

英文摘要:

Achieving the capability of adapting to ever-changing environments is a critical step towards building fully autonomous robots that operate safely in complicated scenarios. In multiagent competitive scenarios, agents may have to adapt to new opponents with previously unseen behaviors by learning from the interaction experiences between the ego-agent and the opponent. However, this adaptation is susceptible to opponent exploitation. As the ego-agent updates its own behavior to exploit the opponent, its own behavior could become more exploitable as a result of overfitting to this specific opponent's behavior. To overcome this difficulty, we developed a safe adaptation approach in which the ego-agent is trained against a regularized opponent model, which effectively avoids overfitting and consequently improves the robustness of the ego-agent's policy. We evaluated our approach in the Mujoco domain with two competing agents. The experiment results suggest that our approach effectively achieves both adaptation to the specific opponent that the ego-agent is interacting with and maintaining low exploitability to other possible opponent exploitation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑