147 citations · 175 across the 7 of their papers we have counts for
6 papers · 1 filter
Cliff Diving: Exploring Reward Surfaces in Reinforcement Learning Environments
Ryan Sullivan, J. K. Terry, Benjamin Black +1
Visualizing optimization landscapes has led to many fundamental insights in numeric optimization, and novel improvements to optimization techniques. However, visualizations of the…
PettingZoo: Gym for Multi-Agent Reinforcement Learning
J. K. Terry, Benjamin Black, Nathaniel Grammel +10
This paper introduces the PettingZoo library and the accompanying Agent Environment Cycle ("AEC") games model. PettingZoo is a library of diverse sets of multi-agent environments w…
Agent Environment Cycle Games
J K Terry, Nathaniel Grammel, Benjamin Black +3
Partially Observable Stochastic Games (POSGs) are the most general and common model of games used in Multi-Agent Reinforcement Learning (MARL). We argue that the POSG model is conc…
Multiplayer Support for the Arcade Learning Environment
J. 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 St…
SuperSuit: Simple Microwrappers for Reinforcement Learning Environments
J. 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. Despite their ubiquity, no library exists with…
Revisiting Parameter Sharing in Multi-Agent Deep Reinforcement Learning
J. K. Terry, Nathaniel Grammel, Sanghyun Son +2
Parameter sharing, where each agent independently learns a policy with fully shared parameters between all policies, is a popular baseline method for multi-agent deep reinforcement…