paper-with-me

Papers

Lifelong Reinforcement Learning with Modulating Masks

2022-12-21 · Eseoghene Ben-Iwhiwhu, Saptarshi Nath, Praveen K. Pilly, Soheil Kolouri, Andrea Soltoggio

Lifelong learning aims to create AI systems that continuously and incrementally learn during a lifetime, similar to biological learning. Attempts so far have met problems, including catastrophic forgetting, interference among tasks, and the inability to exploit previous knowledge. While considerable research has focused on learning multiple supervised classification tasks that involve changes in the input distribution, lifelong reinforcement learning (LRL) must deal with variations in the state and transition distributions, and in the reward functions. Modulating masks with a fixed backbone network, recently developed for classification, are particularly suitable to deal with such a large spectrum of task variations. In this paper, we adapted modulating masks to work with deep LRL, specifically PPO and IMPALA agents. The comparison with LRL baselines in both discrete and continuous RL tasks shows superior performance. We further investigated the use of a linear combination of previously learned masks to exploit previous knowledge when learning new tasks: not only is learning faster, the algorithm solves tasks that we could not otherwise solve from scratch due to extremely sparse rewards. The results suggest that RL with modulating masks is a promising approach to lifelong learning, to the composition of knowledge to learn increasingly complex tasks, and to knowledge reuse for efficient and faster learning.

📄 PDF Abstract BibTeX arXiv:2212.11110

Code (4)

dlpbc/mask-lrl 공식 구현 pytorch
soltoggio/ct-graph 공식 구현 pytorch
DMIU-ShELL/MOSAIC pytorch
dmiu-shell/deeprl-shell pytorch

Tasks

Lifelong learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Residual Connection 설명 없음
Experience Replay Experience Replay is a replay memory technique used in reinforcement learning where we store the agent’s experiences at each time-step, $e\_{t} = \left(s\_{t}, a\_{t}, r\_{t},…
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Tanh Activation 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
RMSProp RMSProp is an unpublished adaptive learning rate optimizer proposed by Geoff Hinton. The motivation…
Gradient Clipping One difficulty that arises with optimization of deep neural networks is that large parameter gradients can lead an SGD optimizer to update…
V-trace V-trace is an off-policy actor-critic reinforcement learning algorithm that helps tackle the lag between when actions are generated by the actors and when the learner…

Similar Papers 제목 키워드 기반

Sharing Lifelong Reinforcement Learning Knowledge via Modulating Masks

2023-05-18 · Saptarshi Nath, Christos Peridis, Eseoghene Ben-Iwhiwhu, Xinran Liu 외

Lifelong learning agents aim to learn multiple tasks sequentially over a lifetime. This involves the ability to exploit previous knowledge when learning new tasks and to avoid forgetting. Modulating masks, a specific typ…

Lifelong learningreinforcement-learningReinforcement Learning

Some Insights into Lifelong Reinforcement Learning Systems

2020-01-27 · Changjian Li

A lifelong reinforcement learning system is a learning system that has the ability to learn through trail-and-error interaction with the environment over its lifetime. In this paper, I give some arguments to show that th…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Bayesian Exploration for Lifelong Reinforcement Learning

2021-09-29 · Haotian Fu, Shangqun Yu, Michael Littman, George Konidaris

A central question in reinforcement learning (RL) is how to leverage prior knowledge to accelerate learning in new tasks. We propose a Bayesian exploration method for lifelong reinforcement learning (BLRL) that aims to …

Lifelong learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

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. How…

Lifelong learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Model-based Lifelong Reinforcement Learning with Bayesian Exploration

2022-10-20 · Haotian Fu, Shangqun Yu, Michael Littman, George Konidaris

We propose a model-based lifelong reinforcement-learning approach that estimates a hierarchical Bayesian posterior distilling the common structure shared across different tasks. The learned posterior combined with a samp…

modelreinforcement-learningReinforcement LearningReinforcement Learning (RL)