Results 71 to 80 of about 311 (117)

Inverse reinforcement learning for video games

CoRR, 2018
Deep reinforcement learning achieves superhuman performance in a range of video game environments, but requires that a designer manually specify a reward function. It is often easier to provide demonstrations of a target behavior than to design a reward function describing that behavior.
Aaron Tucker 0002, Adam Gleave, Stuart Russell 0001   +2 more
openaire   +2 more sources

Expert-Trajectory-Based Features for Apprenticeship Learning via Inverse Reinforcement Learning for Robotic Manipulation

Applied Sciences
This paper explores the application of Inverse Reinforcement Learning (IRL) in robotics, focusing on inferring reward functions from expert demonstrations of robot arm manipulation tasks.
Francisco J. Naranjo-Campos, Juan G. Victores, Carlos Balaguer   +2 more
doaj   +1 more source

Car-following method based on inverse reinforcement learning for autonomous vehicle decision-making

International Journal of Advanced Robotic Systems, 2018
There are still some problems need to be solved though there are a lot of achievements in the fields of automatic driving. One of those problems is the difficulty of designing a car-following decision-making system for complex traffic conditions.
Hongbo Gao, Guanya Shi, Guotao Xie, Bo Cheng   +3 more
doaj   +1 more source

Inverse Reinforcement Learning in Swarm Systems

International Joint Conference on Autonomous Agents and Multiagent Systems, 2017
Inverse reinforcement learning (IRL) has become a useful tool for learning behavioral models from demonstration data. However, IRL remains mostly unexplored for multi-agent systems. In this paper, we show how the principle of IRL can be extended to homogeneous large-scale problems, inspired by the collective swarming behavior of natural systems.
Adrian Sosic, Wasiur R. KhudaBukhsh, Abdelhak M. Zoubir, Heinz Koeppl   +3 more
openaire   +3 more sources

Culturally-attuned AI: Implicit learning of altruistic cultural values through inverse reinforcement learning.

PLoS ONE
Constructing a universal moral code for artificial intelligence (AI) is challenging because human cultures have different values, norms, and social practices.
Nigini Oliveira, Jasmine Li, Koosha Khalvati, Rodolfo Cortes Barragan, Katharina Reinecke, Andrew N Meltzoff, Rajesh P N Rao   +6 more
doaj   +1 more source

Hippocampus and striatum show distinct contributions to longitudinal changes in value-based learning in middle childhood

eLife
The hippocampal-dependent memory system and striatal-dependent memory system modulate reinforcement learning depending on feedback timing in adults, but their contributions during development remain unclear.
Johannes Falck, Lei Zhang, Laurel Raffington, Johannes Julius Mohn, Jochen Triesch, Christine Heim, Yee Lee Shing   +6 more
doaj   +1 more source

Recursive Deep Inverse Reinforcement Learning

CoRR
Inferring an adversary's goals from exhibited behavior is crucial for counterplanning and non-cooperative multi-agent systems in domains like cybersecurity, military, and strategy games. Deep Inverse Reinforcement Learning (IRL) methods based on maximum entropy principles show promise in recovering adversaries' goals but are typically offline, require ...
Paul Ghanem, Michael Potter, Owen Howell 0001, Pau Closas, Alireza Ramezani, Deniz Erdogmus, Tales Imbiriba   +6 more
openaire   +2 more sources

On the Effective Horizon of Inverse Reinforcement Learning

International Joint Conference on Autonomous Agents and Multiagent Systems
Inverse reinforcement learning (IRL) algorithms often rely on (forward) reinforcement learning or planning, over a given time horizon, to compute an approximately optimal policy for a hypothesized reward function; they then match this policy with expert demonstrations.
Yiqing Xu, Finale Doshi-Velez, David Hsu
openaire   +3 more sources

Driver Behavior Modeling with Subjective Risk‐Driven Inverse Reinforcement Learning

Advanced Intelligent Systems
This paper proposes a subjective risk‐driven driver behavior modeling approach that incorporates drivers’ risk perception into decision‐making. Inspired by cognitive science, the proposed framework decomposes drivers’ internal evaluation into preference,
Yang Liang, Zichao Wang, Zhiwei He, Qingquan Wei, Yong Zuo, Linzhen Nie, Zhishuai Yin   +6 more
doaj   +1 more source

The Virtues of Pessimism in Inverse Reinforcement Learning

CoRR
Inverse Reinforcement Learning (IRL) is a powerful framework for learning complex behaviors from expert demonstrations. However, it traditionally requires repeatedly solving a computationally expensive reinforcement learning (RL) problem in its inner loop. It is desirable to reduce the exploration burden by leveraging expert demonstrations in the inner-
Wu, David, Swamy, Gokul, Bagnell, J. Andrew, Wu, Zhiwei Steven, Choudhury, Sanjiban   +4 more
openaire   +2 more sources