Search Results for author: Edward W. Staley

Found 7 papers, 3 papers with code

To Burst or Not to Burst: Generating and Quantifying Improbable Text

no code implementations27 Jan 2024 Kuleen Sasse, Samuel Barham, Efsun Sarioglu Kayi, Edward W. Staley

While large language models (LLMs) are extremely capable at text generation, their outputs are still distinguishable from human-authored text.

Text Generation

Clipped-Objective Policy Gradients for Pessimistic Policy Optimization

1 code implementation10 Nov 2023 Jared Markowitz, Edward W. Staley

To facilitate efficient learning, policy gradient approaches to deep reinforcement learning (RL) are typically paired with variance reduction measures and strategies for making large but safe policy changes based on a batch of experiences.

Multi-Task Learning Policy Gradient Methods +1

Triangular Dropout: Variable Network Width without Retraining

no code implementations2 May 2022 Edward W. Staley, Jared Markowitz

After training, the layer can be arbitrarily reduced in width to exchange performance for narrowness.

Reinforcement Learning (RL)

The AI Arena: A Framework for Distributed Multi-Agent Reinforcement Learning

1 code implementation9 Mar 2021 Edward W. Staley, Corban G. Rivera, Ashley J. Llorens

Advances in reinforcement learning (RL) have resulted in recent breakthroughs in the application of artificial intelligence (AI) across many different domains.

Multi-agent Reinforcement Learning OpenAI Gym +2

PICO: Primitive Imitation for COntrol

no code implementations22 Jun 2020 Corban G. Rivera, Katie M. Popek, Chace Ashcraft, Edward W. Staley, Kapil D. Katyal, Bart L. Paulhamus

In this work, we explore a novel framework for control of complex systems called Primitive Imitation for Control PICO.

Imitation Learning PICO

TanksWorld: A Multi-Agent Environment for AI Safety Research

1 code implementation25 Feb 2020 Corban G. Rivera, Olivia Lyons, Arielle Summitt, Ayman Fatima, Ji Pak, William Shao, Robert Chalmers, Aryeh Englander, Edward W. Staley, I-Jeng Wang, Ashley J. Llorens

In this work, we introduce the AI safety TanksWorld as an environment for AI safety research with three essential aspects: competing performance objectives, human-machine teaming, and multi-agent competition.

Decision Making

Cannot find the paper you are looking for? You can Submit a new open access paper.