Cliff Diving: Exploring Reward Surfaces in Reinforcement Learning Environments

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.

reinforcement-learning Reinforcement Learning (RL)

Statistically Significant Stopping of Neural Network Training

1 code implementation • 1 Mar 2021 • J. K. Terry, Mario Jayakumar, Kusal De Alwis

The general approach taken when training deep learning classifiers is to save the parameters after every few iterations, train until either a human observer or a simple metric-based heuristic decides the network isn't learning anymore, and then backtrack and pick the saved parameters with the best validation accuracy.

PettingZoo: Gym for Multi-Agent Reinforcement Learning

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

Revisiting Parameter Sharing in Multi-Agent Deep Reinforcement Learning

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