Michael Bowling

Learning Purposeful Behaviour in the Absence of Rewards

2016 · arXiv (Cornell University)

Artificial intelligence is commonly defined as the ability to achieve goals in the world. In the reinforcement learning framework, goals are encoded as reward functions that guide agent behaviour, and the sum of observed rewards …

A Laplacian Framework for Option Discovery in Reinforcement Learning

2017 · arXiv (Cornell University)

Representation learning and option discovery are two of the biggest challenges in reinforcement learning (RL). Proto-value functions (PVFs) are a well-known approach for representation learning in MDPs. In this paper we address the option discovery …

Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning

2019 · International Conference on Machine Learning

When observing the actions of others, humans make inferences about why they acted as they did, and what this implies about the world; humans also use the fact that their actions will be interpreted in …

Low-Variance and Zero-Variance Baselines for Extensive-Form Games

2019 · arXiv (Cornell University)

Extensive-form games (EFGs) are a common model of multi-agent interactions with imperfect information. State-of-the-art algorithms for solving these games typically perform full walks of the game tree that can prove prohibitively slow in large games. …

Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form Games

2021 · arXiv (Cornell University)

Hindsight rationality is an approach to playing general-sum games that prescribes no-regret learning dynamics for individual agents with respect to a set of deviations, and further describes jointly rational behavior among multiple agents with mediated …

Should Models Be Accurate?

2022 · arXiv (Cornell University)

Model-based Reinforcement Learning (MBRL) holds promise for data-efficiency by planning with model-generated experience in addition to learning with experience from the environment. However, in complex or changing environments, models in MBRL will inevitably be imperfect, …

On the Interplay Between Sparsity and Training in Deep Reinforcement Learning

2025 · arXiv (Cornell University)

We study the benefits of different sparse architectures for deep reinforcement learning. In particular, we focus on image-based domains where spatially-biased and fully-connected architectures are common. Using these and several other architectures of equal capacity, …