Alert button
Picture for Taher Jafferjee

Taher Jafferjee

Alert button

Semi-Centralised Multi-Agent Reinforcement Learning with Policy-Embedded Training

Add code
Bookmark button
Alert button
Sep 02, 2022
Taher Jafferjee, Juliusz Ziomek, Tianpei Yang, Zipeng Dai, Jianhong Wang, Matthew Taylor, Kun Shao, Jun Wang, David Mguni

Figure 1 for Semi-Centralised Multi-Agent Reinforcement Learning with Policy-Embedded Training
Figure 2 for Semi-Centralised Multi-Agent Reinforcement Learning with Policy-Embedded Training
Figure 3 for Semi-Centralised Multi-Agent Reinforcement Learning with Policy-Embedded Training
Figure 4 for Semi-Centralised Multi-Agent Reinforcement Learning with Policy-Embedded Training
Viaarxiv icon

SAUTE RL: Almost Surely Safe Reinforcement Learning Using State Augmentation

Add code
Bookmark button
Alert button
Feb 16, 2022
Aivar Sootla, Alexander I. Cowen-Rivers, Taher Jafferjee, Ziyan Wang, David Mguni, Jun Wang, Haitham Bou-Ammar

Figure 1 for SAUTE RL: Almost Surely Safe Reinforcement Learning Using State Augmentation
Figure 2 for SAUTE RL: Almost Surely Safe Reinforcement Learning Using State Augmentation
Figure 3 for SAUTE RL: Almost Surely Safe Reinforcement Learning Using State Augmentation
Figure 4 for SAUTE RL: Almost Surely Safe Reinforcement Learning Using State Augmentation
Viaarxiv icon

Reinforcement Learning in Presence of Discrete Markovian Context Evolution

Add code
Bookmark button
Alert button
Feb 14, 2022
Hang Ren, Aivar Sootla, Taher Jafferjee, Junxiao Shen, Jun Wang, Haitham Bou-Ammar

Figure 1 for Reinforcement Learning in Presence of Discrete Markovian Context Evolution
Figure 2 for Reinforcement Learning in Presence of Discrete Markovian Context Evolution
Figure 3 for Reinforcement Learning in Presence of Discrete Markovian Context Evolution
Figure 4 for Reinforcement Learning in Presence of Discrete Markovian Context Evolution
Viaarxiv icon

DESTA: A Framework for Safe Reinforcement Learning with Markov Games of Intervention

Add code
Bookmark button
Alert button
Oct 27, 2021
David Mguni, Joel Jennings, Taher Jafferjee, Aivar Sootla, Yaodong Yang, Changmin Yu, Usman Islam, Ziyan Wang, Jun Wang

Figure 1 for DESTA: A Framework for Safe Reinforcement Learning with Markov Games of Intervention
Figure 2 for DESTA: A Framework for Safe Reinforcement Learning with Markov Games of Intervention
Figure 3 for DESTA: A Framework for Safe Reinforcement Learning with Markov Games of Intervention
Figure 4 for DESTA: A Framework for Safe Reinforcement Learning with Markov Games of Intervention
Viaarxiv icon

Learning to Shape Rewards using a Game of Switching Controls

Add code
Bookmark button
Alert button
Mar 16, 2021
David Mguni, Jianhong Wang, Taher Jafferjee, Nicolas Perez-Nieves, Wenbin Song, Yaodong Yang, Feifei Tong, Hui Chen, Jiangcheng Zhu, Yali Du, Jun Wang

Figure 1 for Learning to Shape Rewards using a Game of Switching Controls
Figure 2 for Learning to Shape Rewards using a Game of Switching Controls
Figure 3 for Learning to Shape Rewards using a Game of Switching Controls
Figure 4 for Learning to Shape Rewards using a Game of Switching Controls
Viaarxiv icon

Hallucinating Value: A Pitfall of Dyna-style Planning with Imperfect Environment Models

Add code
Bookmark button
Alert button
Jun 08, 2020
Taher Jafferjee, Ehsan Imani, Erin Talvitie, Martha White, Micheal Bowling

Figure 1 for Hallucinating Value: A Pitfall of Dyna-style Planning with Imperfect Environment Models
Figure 2 for Hallucinating Value: A Pitfall of Dyna-style Planning with Imperfect Environment Models
Figure 3 for Hallucinating Value: A Pitfall of Dyna-style Planning with Imperfect Environment Models
Figure 4 for Hallucinating Value: A Pitfall of Dyna-style Planning with Imperfect Environment Models
Viaarxiv icon