Agent Environment Cycle Games

no code implementations • 28 Sep 2020 • Justin K. Terry, Nathaniel Grammel, Benjamin Black, Ananth Hari, Caroline Horsch, Luis Santos

Partially Observable Stochastic Games (POSGs) are the most general and common model of games used in Multi-Agent Reinforcement Learning (MARL).

Multi-agent Reinforcement Learning reinforcement-learning +1

Multiplayer Support for the Arcade Learning Environment

no code implementations • 20 Sep 2020 • Justin K. Terry, Benjamin Black, Luis Santos

The Arcade Learning Environment ("ALE") is a widely used library in the reinforcement learning community that allows easy programmatic interfacing with Atari 2600 games, via the Stella emulator.

Atari Games reinforcement-learning +1

SuperSuit: Simple Microwrappers for Reinforcement Learning Environments

1 code implementation • 17 Aug 2020 • Justin K. Terry, Benjamin Black, Ananth Hari

In reinforcement learning, wrappers are universally used to transform the information that passes between a model and an environment.

reinforcement-learning Reinforcement Learning (RL)

Multi-Agent Informational Learning Processes

no code implementations • 11 Jun 2020 • Justin K. Terry, Nathaniel Grammel

We introduce a new mathematical model of multi-agent reinforcement learning, the Multi-Agent Informational Learning Processor "MAILP" model.

Multi-agent Reinforcement Learning reinforcement-learning +1

Understanding Generalization through Visualizations

2 code implementations • NeurIPS Workshop ICBINB 2020 • W. Ronny Huang, Zeyad Emam, Micah Goldblum, Liam Fowl, Justin K. Terry, Furong Huang, Tom Goldstein

The power of neural networks lies in their ability to generalize to unseen data, yet the underlying reasons for this phenomenon remain elusive.