Michael Dann

21 papers A* 7A 4Journal 5Unranked 5
YearRankTypeTitle / Venue / Authors
2025 A conf
Beyond Goal Recognition: A Reinforcement Learning-based Approach to Inferring Agent Behaviour.
AAMAS
Sheryl Mantik, Michael Dann, Minyi Li, Huong Ha, Julie Porteous
2025 — conf
Evolving MCTS Macro-actions in Real-Time Domains.
AI (2)
Andrew Gourley, Michael Dann, Xiaodong Li, Fabio Zambetta
2025 — conf
Evolving Macro-Actions for MCTS Video Game Agents.
GECCO Companion
Andrew Gourley, Michael Dann, Xiaodong Li, Fabio Zambetta
2024 A* conf
Harnessing Network Effect for Fake News Mitigation: Selecting Debunkers via Self-Imitation Learning.
AAAI
Xiaofei Xu, Ke Deng, Michael Dann, Xiuzhen Zhang
2024 J jnl
Harnessing Network Effect for Fake News Mitigation: Selecting Debunkers via Self-Imitation Learning.
CoRR
Xiaofei Xu, Ke Deng, Michael Dann, Xiuzhen Zhang
2023 A conf
Feedback-Guided Intention Scheduling for BDI Agents.
AAMAS
Michael Dann, John Thangarajah, Minyi Li
2023 A* conf
Multi-Agent Intention Recognition and Progression.
IJCAI
Michael Dann, Yuan Yao, Natasha Alechina, Brian Logan, Felipe Meneguzzi, John Thangarajah
2023 — conf
SAGE: Generating Symbolic Goals for Myopic Models in Deep Reinforcement Learning.
AI (2)
Andrew Chester, Michael Dann, Fabio Zambetta, John Thangarajah
2022 A* conf
Multi-Agent Intention Progression with Reward Machines.
IJCAI
Michael Dann, Yuan Yao, Natasha Alechina, Brian Logan, John Thangarajah
2022 — conf
Oracle-SAGE: Planning Ahead in Graph-Based Deep Reinforcement Learning.
ECML/PKDD (4)
Andrew Chester, Michael Dann, Fabio Zambetta, John Thangarajah
2022 J jnl
SAGE: Generating Symbolic Goals for Myopic Models in Deep Reinforcement Learning.
CoRR
Andrew Chester, Michael Dann, Fabio Zambetta, John Thangarajah
2021 A* conf
Adapting to Reward Progressivity via Spectral Reinforcement Learning.
ICLR
Michael Dann, John Thangarajah
2021 J jnl
Adapting to Reward Progressivity via Spectral Reinforcement Learning.
CoRR
Michael Dann, John Thangarajah
2021 A* conf
Multi-Agent Intention Progression with Black-Box Agents.
IJCAI
Michael Dann, Yuan Yao, Brian Logan, John Thangarajah
2020 A conf
Intention-Aware Multiagent Scheduling.
AAMAS
Michael Dann, John Thangarajah, Yuan Yao, Brian Logan
2019 A* conf
Deriving Subgoals Autonomously to Accelerate Learning in Sparse Reward Domains.
AAAI
Michael Dann, Fabio Zambetta, John Thangarajah
2018 J jnl
Exploration in Continuous Control Tasks via Continually Parameterized Skills.
IEEE Trans. Games
Michael Dann, Fabio Zambetta, John Thangarajah
2018 J jnl
Integrating Skills and Simulation to Solve Complex Navigation Tasks in Infinite Mario.
IEEE Trans. Games
Michael Dann, Fabio Zambetta, John Thangarajah
2017 A* conf
Real-Time Navigation in Classical Platform Games via Skill Reuse.
IJCAI
Michael Dann, Fabio Zambetta, John Thangarajah
2017 A conf
Reusing Skills for First-Time Solution of Navigation Tasks in Platform Videogames.
AAMAS
Michael Dann, Fabio Zambetta, John Thangarajah
2015 — conf
An improved approach to reinforcement learning in Computer Go.
CIG
Michael Dann, Fabio Zambetta, John Thangarajah