Search Results for author:
Found 6 papers, 1 papers with code
PSI Draft Specification
This document presents the draft specification for delivering machine learning services over HTTP, developed as part of the Protocols and Structures for Inference project, which concluded in 2013.
Uncovering Surprising Behaviors in Reinforcement Learning via Worst-case Analysis
Reinforcement learning agents are typically trained and evaluated according to their performance averaged over some distribution of environment settings.
Rigorous Agent Evaluation: An Adversarial Approach to Uncover Catastrophic Failures
We demonstrate this is an issue for current agents, where even matching the compute used for training is sometimes insufficient for evaluation.
Human-level performance in first-person multiplayer games with population-based deep reinforcement learning
Recent progress in artificial intelligence through reinforcement learning (RL) has shown great success on increasingly complex single-agent environments and two-player turn-based games.
Pooling is neither necessary nor sufficient for appropriate deformation stability in CNNs
In this work, we rigorously test these questions, and find that deformation stability in convolutional networks is more nuanced than it first appears: (1) Deformation invariance is not a binary property, but rather that different tasks require different degrees of deformation stability at different layers.
Model-Free Episodic Control
State of the art deep reinforcement learning algorithms take many millions of interactions to attain human-level performance.
