34 citations · 79 across the 6 of their papers we have counts for
6 papers
The Effect of Planning Shape on Dyna-style Planning in High-dimensional State Spaces
G. Zacharias Holland, Erin J. Talvitie, Michael Bowling
Dyna is a fundamental approach to model-based reinforcement learning (MBRL) that interleaves planning, acting, and learning in an online setting. In the most typical application of…
Learning the Reward Function for a Misspecified Model
Erik Talvitie
In model-based reinforcement learning it is typical to decouple the problems of learning the dynamics model and learning the reward function. However, when the dynamics model is fl…
Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents
Marlos C. Machado, Marc G. Bellemare, Erik Talvitie +3
The Arcade Learning Environment (ALE) is an evaluation platform that poses the challenge of building AI agents with general competency across dozens of Atari 2600 games. It support…
Self-Correcting Models for Model-Based Reinforcement Learning
Erik Talvitie
When an agent cannot represent a perfectly accurate model of its environment's dynamics, model-based reinforcement learning (MBRL) can fail catastrophically. Planning involves comp…
State of the Art Control of Atari Games Using Shallow Reinforcement Learning
Yitao Liang, Marlos C. Machado, Erik Talvitie +1
The recently introduced Deep Q-Networks (DQN) algorithm has gained attention as one of the first successful combinations of deep neural networks and reinforcement learning. Its pro…
Learning to Make Predictions In Partially Observable Environments Without a Generative Model
Erik Talvitie, Satinder Singh
When faced with the problem of learning a model of a high-dimensional environment, a common approach is to limit the model to make only a restricted set of predictions, thereby sim…