Attentive Multi-Task Deep Reinforcement Learning

2019-07-05 · Timo Bram, Gino Brunner, Oliver Richter, Roger Wattenhofer

Sharing knowledge between tasks is vital for efficient learning in a multi-task setting. However, most research so far has focused on the easier case where knowledge transfer is not harmful, i.e., where knowledge from one task cannot negatively impact the performance on another task. In contrast, we present an approach to multi-task deep reinforcement learning based on attention that does not require any a-priori assumptions about the relationships between tasks. Our attention network automatically groups task knowledge into sub-networks on a state level granularity. It thereby achieves positive knowledge transfer if possible, and avoids negative transfer in cases where tasks interfere. We test our algorithm against two state-of-the-art multi-task/transfer learning approaches and show comparable or superior performance while requiring fewer network parameters.

📄 PDF Abstract BibTeX arXiv:1907.02874

Code (1)

braemt/attentive-multi-task-deep-reinforcement-learning 공식 구현 tf

Tasks

Deep Reinforcement Learningreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Transfer Learning

Crossmodal Attentive Skill Learner

2017-11-28 · Shayegan Omidshafiei, Dong-Ki Kim, Jason Pazis, Jonathan P. How

This paper presents the Crossmodal Attentive Skill Learner (CASL), integrated with the recently-introduced Asynchronous Advantage Option-Critic (A2OC) architecture [Harb et al., 2017] to enable hierarchical reinforcement…

Atari Games CPU GPU Hierarchical Reinforcement Learning+3

Intelligent Electric Vehicle Charging Recommendation Based on Multi-Agent Reinforcement Learning

2021-02-15 · Weijia Zhang, Hao liu, Fan Wang, Tong Xu 외

Electric Vehicle (EV) has become a preferable choice in the modern transportation system due to its environmental and energy sustainability. However, in many large cities, EV drivers often fail to find the proper spots f…

Deep Reinforcement Learning Multi-agent Reinforcement Learning Multi-Objective Multi-Agent Reinforcement Learning reinforcement-learning+2

Neural Consciousness Flow

2019-05-30 · Xiaoran Xu, Wei Feng, Zhiqing Sun, Zhi-Hong Deng

The ability of reasoning beyond data fitting is substantial to deep learning systems in order to make a leap forward towards artificial general intelligence. A lot of efforts have been made to model neural-based reasonin…

Decision Making Knowledge Base Completion Reinforcement Learning

Rationally Inattentive Inverse Reinforcement Learning Explains YouTube Commenting Behavior

2019-10-24 · William Hoiles, Vikram Krishnamurthy, Kunal Pattanayak

We consider a novel application of inverse reinforcement learning with behavioral economics constraints to model, learn and predict the commenting behavior of YouTube viewers. Each group of users is modeled as a rational…

Clustering reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Boosting Value Decomposition via Unit-Wise Attentive State Representation for Cooperative Multi-Agent Reinforcement Learning

2023-05-12 · Qingpeng Zhao, Yuanyang Zhu, Zichuan Liu, Zhi Wang 외

In cooperative multi-agent reinforcement learning (MARL), the environmental stochasticity and uncertainties will increase exponentially when the number of agents increases, which puts hard pressure on how to come up with…

Multi-agent Reinforcement Learning Starcraft Starcraft II