Improving Generalization in Meta Reinforcement Learning using Learned Objectives
Biological evolution has distilled the experiences of many learners into the general learning algorithms of humans. Our novel meta reinforcement learning algorithm MetaGenRL is inspired by this process. MetaGenRL distills the experiences of many complex agents to meta-learn a low-complexity neural objective function that decides how future individuals will learn. Unlike recent meta-RL algorithms, MetaGenRL can generalize to new environments that are entirely different from those used for meta-training. In some cases, it even outperforms human-engineered RL algorithms. MetaGenRL uses off-policy second-order gradients during meta-training that greatly increase its sample efficiency.
Code (0)
등록된 구현이 없습니다.
Tasks
Meta Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Meta-Learning for Multi-objective Reinforcement Learning
Multi-objective reinforcement learning (MORL) is the generalization of standard reinforcement learning (RL) approaches to solve sequential decision making problems that consist of several, possibly conflicting, objective…
Computational Efficiencycontinuous-controlContinuous ControlDecision Making+6Scalable Multi-Objective and Meta Reinforcement Learning via Gradient Estimation
We study the problem of efficiently estimating policies that simultaneously optimize multiple objectives in reinforcement learning (RL). Given $n$ objectives (or tasks), we seek the optimal partition of these objectives …
Reinforcement LearningRobust Driving Policy Learning with Guided Meta Reinforcement Learning
Although deep reinforcement learning (DRL) has shown promising results for autonomous navigation in interactive traffic scenarios, existing work typically adopts a fixed behavior policy to control social vehicles in the …
Autonomous NavigationDeep Reinforcement LearningMeta Reinforcement Learningreinforcement-learning+1Higher-Order Generalization Bounds: Learning Deep Probabilistic Programs via PAC-Bayes Objectives
Deep Probabilistic Programming (DPP) allows powerful models based on recursive computation to be learned using efficient deep-learning optimization techniques. Additionally, DPP offers a unified perspective, where infere…
Generalization BoundsMeta-LearningProbabilistic ProgrammingMulti-Task Reinforcement Learning with Language-Encoded Gated Policy Networks
Multi-task reinforcement learning often relies on task metadata -- such as brief natural-language descriptions -- to guide behavior across diverse objectives. We present Lexical Policy Networks (LEXPOL), a language-condi…
Reinforcement Learning