no code implementations • 14 May 2022 • Ryan Sullivan, J. K. Terry, Benjamin Black, John P. Dickerson
Visualizing optimization landscapes has led to many fundamental insights in numeric optimization, and novel improvements to optimization techniques.
no code implementations • 23 Feb 2021 • Gregory Cooke, Dan Marsh, Catherine Walsh, Benjamin Black, Jean-François Lamarque
Using a three-dimensional chemistry-climate model, we simulate changes in O$_3$ in Earth's atmosphere since the GOE and consider the implications for surface habitability, and glaciation during the Mesoproterozoic.
Earth and Planetary Astrophysics Atmospheric and Oceanic Physics Geophysics
2 code implementations • NeurIPS 2021 • J. K. Terry, Benjamin Black, Nathaniel Grammel, Mario Jayakumar, Ananth Hari, Ryan Sullivan, Luis Santos, Rodrigo Perez, Caroline Horsch, Clemens Dieffendahl, Niall L. Williams, Yashas Lokesh, Praveen Ravi
This paper introduces the PettingZoo library and the accompanying Agent Environment Cycle ("AEC") games model.
Multi-agent Reinforcement Learning reinforcement-learning +1
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
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.
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.
2 code implementations • 27 May 2020 • J. K. Terry, Nathaniel Grammel, Sanghyun Son, Benjamin Black, Aakriti Agrawal
Next, we formally introduce methods to extend parameter sharing to learning in heterogeneous observation and action spaces, and prove that these methods allow for convergence to optimal policies.
Multi-agent Reinforcement Learning reinforcement-learning +1