Knowledge Transfer in Model-Based Reinforcement Learning Agents for Efficient Multi-Task Learning
We propose an efficient knowledge transfer approach for model-based reinforcement learning, addressing the challenge of deploying large world models in resource-constrained environments. Our method distills a high-capacity multi-task agent (317M parameters) into a compact 1M parameter model, achieving state-of-the-art performance on the MT30 benchmark with a normalized score of 28.45, a substantial improvement over the original 1M parameter model's score of 18.93. This demonstrates the ability of our distillation technique to consolidate complex multi-task knowledge effectively. Additionally, we apply FP16 post-training quantization, reducing the model size by 50% while maintaining performance. Our work bridges the gap between the power of large models and practical deployment constraints, offering a scalable solution for efficient and accessible multi-task reinforcement learning in robotics and other resource-limited domains.
Code (0)
등록된 구현이 없습니다.
Tasks
Model-based Reinforcement LearningMulti-Task LearningQuantizationreinforcement-learningReinforcement LearningTransfer LearningSimilar Papers 제목 키워드 기반
Centralized Reward Agent for Knowledge Sharing and Transfer in Multi-Task Reinforcement Learning
Reward shaping is effective in addressing the sparse-reward challenge in reinforcement learning by providing immediate feedback through auxiliary informative rewards. Based on the reward shaping strategy, we propose a no…
reinforcement-learningReinforcement LearningParallel Knowledge Transfer in Multi-Agent Reinforcement Learning
Multi-agent reinforcement learning is a standard framework for modeling multi-agent interactions applied in real-world scenarios. Inspired by experience sharing in human groups, learning knowledge parallel reusing betwee…
Multi-agent Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)+2Learning Where, What and How to Transfer: A Multi-Role Reinforcement Learning Approach for Evolutionary Multitasking
Evolutionary multitasking (EMT) algorithms typically require tailored designs for knowledge transfer, in order to assure convergence and optimality in multitask optimization. In this paper, we explore designing a systema…
Reinforcement LearningSharing Lifelong Reinforcement Learning Knowledge via Modulating Masks
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 LearningExpert-Free Online Transfer Learning in Multi-Agent Reinforcement Learning
Transfer learning in Reinforcement Learning (RL) has been widely studied to overcome training issues of Deep-RL, i.e., exploration cost, data availability and convergence time, by introducing a way to enhance training ph…
Multi-agent Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1