Safe Policy Search for Lifelong Reinforcement Learning with Sublinear Regret

2015-05-21 · Haitham Bou Ammar, Rasul Tutunov, Eric Eaton

Lifelong reinforcement learning provides a promising framework for developing versatile agents that can accumulate knowledge over a lifetime of experience and rapidly learn new tasks by building upon prior knowledge. However, current lifelong learning methods exhibit non-vanishing regret as the amount of experience increases and include limitations that can lead to suboptimal or unsafe control policies. To address these issues, we develop a lifelong policy gradient learner that operates in an adversarial set- ting to learn multiple tasks online while enforcing safety constraints on the learned policies. We demonstrate, for the first time, sublinear regret for lifelong policy search, and validate our algorithm on several benchmark dynamical systems and an application to quadrotor control.

📄 PDF Abstract BibTeX arXiv:1505.05798

Code (0)

등록된 구현이 없습니다.

Tasks

Lifelong learningreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Provably Efficient Lifelong Reinforcement Learning with Linear Function Approximation

2022-06-01 · Sanae Amani, Lin F. Yang, Ching-An Cheng

We study lifelong reinforcement learning (RL) in a regret minimization setting of linear contextual Markov decision process (MDP), where the agent needs to learn a multi-task policy while solving a streaming sequence of …

4k Lifelong learning reinforcement-learning Reinforcement Learning+1

Fast Lifelong Adaptive Inverse Reinforcement Learning from Demonstrations

2022-09-24 · Letian Chen, Sravan Jayanthi, Rohan Paleja, Daniel Martin 외

Learning from Demonstration (LfD) approaches empower end-users to teach robots novel tasks via demonstrations of the desired behaviors, democratizing access to robotics. However, current LfD frameworks are not capable of…

Continuous Control reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Reactive Exploration to Cope with Non-Stationarity in Lifelong Reinforcement Learning

2022-07-12 · Christian Steinparz, Thomas Schmied, Fabian Paischer, Marius-Constantin Dinu 외

In lifelong learning, an agent learns throughout its entire life without resets, in a constantly changing environment, as we humans do. Consequently, lifelong learning comes with a plethora of research problems such as c…

Lifelong learning Policy Gradient Methods Q-Learning reinforcement-learning+1

Statistical Guarantees for Lifelong Reinforcement Learning using PAC-Bayes Theory

2024-11-01 · Zhi Zhang, Chris Chow, Yasi Zhang, Yanchao Sun 외

Lifelong reinforcement learning (RL) has been developed as a paradigm for extending single-task RL to more realistic, dynamic settings. In lifelong RL, the "life" of an RL agent is modeled as a stream of tasks drawn from…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Lifelong Bandit Optimization: No Prior and No Regret

2022-10-27 · Felix Schur, Parnian Kassraie, Jonas Rothfuss, Andreas Krause

Machine learning algorithms are often repeatedly applied to problems with similar structure over and over again. We focus on solving a sequence of bandit optimization tasks and develop LIBO, an algorithm which adapts to …