Zobrazeno 1 - 10
of 44
pro vyhledávání: '"Qiu, Tenghai"'
Multi-task reinforcement learning (MTRL) demonstrate potential for enhancing the generalization of a robot, enabling it to perform multiple tasks concurrently. However, the performance of MTRL may still be susceptible to conflicts between tasks and n
Externí odkaz:
http://arxiv.org/abs/2404.05950
Multi-Agent Reinforcement Learning (MARL) has been successful in solving many cooperative challenges. However, classic non-hierarchical MARL algorithms still cannot address various complex multi-agent problems that require hierarchical cooperative be
Externí odkaz:
http://arxiv.org/abs/2403.18056
Large-scale heterogeneous multiagent systems feature various realistic factors in the real world, such as agents with diverse abilities and overall system cost. In comparison to homogeneous systems, heterogeneous systems offer significant practical a
Externí odkaz:
http://arxiv.org/abs/2403.18057
Diversity plays a crucial role in improving the performance of multi-agent reinforcement learning (MARL). Currently, many diversity-based methods have been developed to overcome the drawbacks of excessive parameter sharing in traditional MARL. Howeve
Externí odkaz:
http://arxiv.org/abs/2401.11257
Publikováno v:
2023 World Congress of the International Federation of Automatic Control
Many multiagent systems in the real world include multiple types of agents with different abilities and functionality. Such heterogeneous multiagent systems have significant practical advantages. However, they also come with challenges compared with
Externí odkaz:
http://arxiv.org/abs/2211.11616
SOTA multiagent reinforcement algorithms distinguish themselves in many ways from their single-agent equivalences. However, most of them still totally inherit the single-agent exploration-exploitation strategy. Naively inheriting this strategy from s
Externí odkaz:
http://arxiv.org/abs/2208.07753
Multiagent reinforcement learning (MARL) can solve complex cooperative tasks. However, the efficiency of existing MARL methods relies heavily on well-defined reward functions. Multiagent tasks with sparse reward feedback are especially challenging no
Externí odkaz:
http://arxiv.org/abs/2208.03002
When dealing with a series of imminent issues, humans can naturally concentrate on a subset of these concerning issues by prioritizing them according to their contributions to motivational indices, e.g., the probability of winning a game. This idea o
Externí odkaz:
http://arxiv.org/abs/2203.06416
Publikováno v:
In Computers and Electrical Engineering August 2024 118 Part A
Publikováno v:
In IFAC PapersOnLine 2023 56(2):3033-3040