Exploration in environments with sparse rewards is difficult for artificial agents. Curiosity driven learning -- using feed-forward prediction errors as intrinsic rewards -- has achieved some success in these scenarios, but fails when faced with action-dependent noise sources. We present aleatoric mapping agents (AMAs), a neuroscience inspired solution modeled on the cholinergic system of the mammalian brain. AMAs aim to explicitly ascertain which dynamics of the environment are unpredictable, regardless of whether those dynamics are induced by the actions of the agent. This is achieved by generating separate forward predictions for the mean and variance of future states and reducing intrinsic rewards for those transitions with high aleatoric variance. We show AMAs are able to effectively circumvent action-dependent stochastic traps that immobilise conventional curiosity driven agents. The code for all experiments presented in this paper is open sourced: http://github.com/self-supervisor/Escaping-Stochastic-Traps-With-Aleatoric-Mapping-Agents.
翻译:人工剂很难在环境里进行回报微薄的探索。 由好奇力驱动的学习 -- -- 将进化预测错误作为内在的回报 -- -- 在这些情景中取得了一些成功,但在面对依赖行动的噪音源时却失败了。 我们展示了以哺乳动物大脑的胆碱基系统为模型的神经科学启发型解决方案AMAs。 AMAs旨在明确确定环境的哪些动态是无法预测的,而不论这些动态是否是由该剂的行为引起的。这是通过分别预测未来状态的平均值和差异,并减少这些变化的内在回报而实现的。 我们显示, AMAs能够有效地绕过依赖行动的切析陷阱,使传统的好奇力驱动剂无法移动。 本文提出的所有实验的代码都是开源的 : http://github. com/sel- supervisor/ Escaping-Stochastic- trapts- with-Aleator-Mappic-Agents。