Michael Bowling
University of Alberta · 296 works · 9,964 citations · h-index 48
Top works
- The Arcade Learning Environment: An Evaluation Platform for General Agents
- Investigating Contingency Awareness Using Atari 2600 Games
- The Arcade Learning Environment: An Evaluation Platform for General Agents
- DeepStack: Expert-level artificial intelligence in heads-up no-limit poker
- Multiagent learning using a variable learning rate
- Regret Minimization in Games with Incomplete Information
- Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents
- Automatic gait optimization with Gaussian process regression
- Heads-up limit hold’em poker is solved
- Rational and convergent learning in stochastic games
- Convergence of Gradient Dynamics with a Variable Learning Rate
- Sketch-Based Linear Value Function Approximation
- Apprenticeship learning using linear programming
- Bayesian Learning of Recursively Factored Environments
- Action respecting embedding
- Bayesian sparse sampling for on-line reward optimization
- Convergence and No-Regret in Multiagent Learning
- Monte Carlo Sampling for Regret Minimization in Extensive Games
- STP: Skills, tactics, and plays for multi-robot control in adversarial environments
- The Hanabi challenge: A new frontier for AI research