Search Results for author: Matthew Hausknecht

Found 27 papers, 15 papers with code

Beyond Short Snippets: Deep Networks for Video Classification

1 code implementation CVPR 2015 Joe Yue-Hei Ng, Matthew Hausknecht, Sudheendra Vijayanarasimhan, Oriol Vinyals, Rajat Monga, George Toderici

Convolutional neural networks (CNNs) have been extensively applied for image recognition problems giving state-of-the-art results on recognition, detection, segmentation and retrieval.

Action Recognition Classification +4

Deep Recurrent Q-Learning for Partially Observable MDPs

5 code implementations23 Jul 2015 Matthew Hausknecht, Peter Stone

Deep Reinforcement Learning has yielded proficient controllers for complex tasks.

Atari Games OpenAI Gym +1

Deep Reinforcement Learning in Parameterized Action Space

7 code implementations13 Nov 2015 Matthew Hausknecht, Peter Stone

Recent work has shown that deep neural networks are capable of approximating both value functions and policies in reinforcement learning domains featuring continuous state and action spaces.

reinforcement-learning Reinforcement Learning (RL)

Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents

7 code implementations18 Sep 2017 Marlos C. Machado, Marc G. Bellemare, Erik Talvitie, Joel Veness, Matthew Hausknecht, Michael Bowling

The Arcade Learning Environment (ALE) is an evaluation platform that poses the challenge of building AI agents with general competency across dozens of Atari 2600 games.

Atari Games

Neural Program Meta-Induction

no code implementations NeurIPS 2017 Jacob Devlin, Rudy Bunel, Rishabh Singh, Matthew Hausknecht, Pushmeet Kohli

In our first proposal, portfolio adaptation, a set of induction models is pretrained on a set of related tasks, and the best model is adapted towards the new task using transfer learning.

Program induction Transfer Learning

Now I Remember! Episodic Memory For Reinforcement Learning

no code implementations ICLR 2018 Ricky Loynd, Matthew Hausknecht, Lihong Li, Li Deng

Humans rely on episodic memory constantly, in remembering the name of someone they met 10 minutes ago, the plot of a movie as it unfolds, or where they parked the car.

reinforcement-learning Reinforcement Learning (RL)

Counting to Explore and Generalize in Text-based Games

2 code implementations29 Jun 2018 Xingdi Yuan, Marc-Alexandre Côté, Alessandro Sordoni, Romain Laroche, Remi Tachet des Combes, Matthew Hausknecht, Adam Trischler

We propose a recurrent RL agent with an episodic exploration mechanism that helps discovering good policies in text-based game environments.

text-based games

ScriptNet: Neural Static Analysis for Malicious JavaScript Detection

no code implementations1 Apr 2019 Jack W. Stokes, Rakshit Agrawal, Geoff McDonald, Matthew Hausknecht

We use the Convoluted Partitioning of Long Sequences (CPoLS) model, which processes Javascript files as byte sequences.

Multi-Preference Actor Critic

no code implementations5 Apr 2019 Ishan Durugkar, Matthew Hausknecht, Adith Swaminathan, Patrick MacAlpine

Policy gradient algorithms typically combine discounted future rewards with an estimated value function, to compute the direction and magnitude of parameter updates.

reinforcement-learning Reinforcement Learning (RL)

Interactive Fiction Games: A Colossal Adventure

4 code implementations11 Sep 2019 Matthew Hausknecht, Prithviraj Ammanabrolu, Marc-Alexandre Côté, Xingdi Yuan

A hallmark of human intelligence is the ability to understand and communicate with language.

Learning Calibratable Policies using Programmatic Style-Consistency

2 code implementations ICML 2020 Eric Zhan, Albert Tseng, Yisong Yue, Adith Swaminathan, Matthew Hausknecht

We study the problem of controllable generation of long-term sequential behaviors, where the goal is to calibrate to multiple behavior styles simultaneously.

Imitation Learning

Working Memory Graphs

no code implementations ICML 2020 Ricky Loynd, Roland Fernandez, Asli Celikyilmaz, Adith Swaminathan, Matthew Hausknecht

Transformers have increasingly outperformed gated RNNs in obtaining new state-of-the-art results on supervised tasks involving text sequences.

Decision Making

How to Avoid Being Eaten by a Grue: Structured Exploration Strategies for Textual Worlds

1 code implementation12 Jun 2020 Prithviraj Ammanabrolu, Ethan Tien, Matthew Hausknecht, Mark O. Riedl

Text-based games are long puzzles or quests, characterized by a sequence of sparse and potentially deceptive rewards.

text-based games

Keep CALM and Explore: Language Models for Action Generation in Text-based Games

1 code implementation EMNLP 2020 Shunyu Yao, Rohan Rao, Matthew Hausknecht, Karthik Narasimhan

In this paper, we propose the Contextual Action Language Model (CALM) to generate a compact set of action candidates at each game state.

Action Generation Language Modelling +1

ALFWorld: Aligning Text and Embodied Environments for Interactive Learning

1 code implementation8 Oct 2020 Mohit Shridhar, Xingdi Yuan, Marc-Alexandre Côté, Yonatan Bisk, Adam Trischler, Matthew Hausknecht

ALFWorld enables the creation of a new BUTLER agent whose abstract knowledge, learned in TextWorld, corresponds directly to concrete, visually grounded actions.

Natural Language Visual Grounding Scene Understanding

BUTLER: Building Understanding in TextWorld via Language for Embodied Reasoning

no code implementations ICLR 2021 Mohit Shridhar, Xingdi Yuan, Marc-Alexandre Cote, Yonatan Bisk, Adam Trischler, Matthew Hausknecht

ALFWorld enables the creation of a new BUTLER agent whose abstract knowledge, learned in TextWorld, corresponds directly to concrete, visually grounded actions.

Scene Understanding

Consistent Dropout for Policy Gradient Reinforcement Learning

no code implementations23 Feb 2022 Matthew Hausknecht, Nolan Wagener

Dropout has long been a staple of supervised learning, but is rarely used in reinforcement learning.

reinforcement-learning Reinforcement Learning (RL)

MoCapAct: A Multi-Task Dataset for Simulated Humanoid Control

1 code implementation15 Aug 2022 Nolan Wagener, Andrey Kolobov, Felipe Vieira Frujeri, Ricky Loynd, Ching-An Cheng, Matthew Hausknecht

We demonstrate the utility of MoCapAct by using it to train a single hierarchical policy capable of tracking the entire MoCap dataset within dm_control and show the learned low-level component can be re-used to efficiently learn downstream high-level tasks.

Humanoid Control

UniMASK: Unified Inference in Sequential Decision Problems

1 code implementation20 Nov 2022 Micah Carroll, Orr Paradise, Jessy Lin, Raluca Georgescu, Mingfei Sun, David Bignell, Stephanie Milani, Katja Hofmann, Matthew Hausknecht, Anca Dragan, Sam Devlin

Randomly masking and predicting word tokens has been a successful approach in pre-training language models for a variety of downstream tasks.

Decision Making

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