Zobrazeno 1 - 10
of 119
pro vyhledávání: '"Tesauro, Gerald"'
Humans learn quickly even in tasks that contain complex visual information. This is due in part to the efficient formation of compressed representations of visual information, allowing for better generalization and robustness. However, compressed rep
Externí odkaz:
http://arxiv.org/abs/2303.17508
Autor:
Kim, Dong-Ki, Riemer, Matthew, Liu, Miao, Foerster, Jakob N., Tesauro, Gerald, How, Jonathan P.
Multiagent learning settings are inherently more difficult than single-agent learning because each agent interacts with other simultaneously learning agents in a shared environment. An effective approach in multiagent reinforcement learning is to con
Externí odkaz:
http://arxiv.org/abs/2210.16175
Autor:
Kim, Dong-Ki, Riemer, Matthew, Liu, Miao, Foerster, Jakob N., Everett, Michael, Sun, Chuangchuang, Tesauro, Gerald, How, Jonathan P.
The main challenge of multiagent reinforcement learning is the difficulty of learning useful policies in the presence of other simultaneously learning agents whose changing behaviors jointly affect the environment's transition and reward dynamics. An
Externí odkaz:
http://arxiv.org/abs/2203.03535
Hierarchical reinforcement learning has focused on discovering temporally extended actions, such as options, that can provide benefits in problems requiring extensive exploration. One promising approach that learns these options end-to-end is the opt
Externí odkaz:
http://arxiv.org/abs/2109.09876
This paper introduces an information-theoretic constraint on learned policy complexity in the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) reinforcement learning algorithm. Previous research with a related approach in continuous control ex
Externí odkaz:
http://arxiv.org/abs/2011.11517
Autor:
Kim, Dong-Ki, Liu, Miao, Riemer, Matthew, Sun, Chuangchuang, Abdulhai, Marwa, Habibi, Golnaz, Lopez-Cot, Sebastian, Tesauro, Gerald, How, Jonathan P.
A fundamental challenge in multiagent reinforcement learning is to learn beneficial behaviors in a shared environment with other simultaneously learning agents. In particular, each agent perceives the environment as effectively non-stationary due to
Externí odkaz:
http://arxiv.org/abs/2011.00382
Biological agents learn and act intelligently in spite of a highly limited capacity to process and store information. Many real-world problems involve continuous control, which represents a difficult task for artificial intelligence agents. In this p
Externí odkaz:
http://arxiv.org/abs/2010.04646
Autor:
Murugesan, Keerthiram, Atzeni, Mattia, Kapanipathi, Pavan, Shukla, Pushkar, Kumaravel, Sadhana, Tesauro, Gerald, Talamadupula, Kartik, Sachan, Mrinmaya, Campbell, Murray
Text-based games have emerged as an important test-bed for Reinforcement Learning (RL) research, requiring RL agents to combine grounded language understanding with sequential decision making. In this paper, we examine the problem of infusing RL agen
Externí odkaz:
http://arxiv.org/abs/2010.03790
Autor:
Allen, Cameron, Katz, Michael, Klinger, Tim, Konidaris, George, Riemer, Matthew, Tesauro, Gerald
The difficulty of deterministic planning increases exponentially with search-tree depth. Black-box planning presents an even greater challenge, since planners must operate without an explicit model of the domain. Heuristics can make search more effic
Externí odkaz:
http://arxiv.org/abs/2004.13242
The options framework is a popular approach for building temporally extended actions in reinforcement learning. In particular, the option-critic architecture provides general purpose policy gradient theorems for learning actions from scratch that are
Externí odkaz:
http://arxiv.org/abs/1912.13408