About

Benchmarks

No evaluation results yet. Help compare methods by submit evaluation metrics.

Datasets

Latest papers without code

Reinforcement Learning of Implicit and Explicit Control Flow in Instructions

25 Feb 2021

Learning to flexibly follow task instructions in dynamic environments poses interesting challenges for reinforcement learning agents.

MINECRAFT STARCRAFT

Program Synthesis Guided Reinforcement Learning

22 Feb 2021

We propose an approach that leverages program synthesis to automatically generate the guiding program.

MINECRAFT PROGRAM SYNTHESIS

Clockwork Variational Autoencoders

18 Feb 2021

We introduce the Clockwork VAE (CW-VAE), a video prediction model that leverages a hierarchy of latent sequences, where higher levels tick at slower intervals.

MINECRAFT VIDEO PREDICTION

The MineRL 2020 Competition on Sample Efficient Reinforcement Learning using Human Priors

26 Jan 2021

Although deep reinforcement learning has led to breakthroughs in many difficult domains, these successes have required an ever-increasing number of samples, affording only a shrinking segment of the AI community access to their development.

DECISION MAKING EFFICIENT EXPLORATION MINECRAFT

Autonomous Learning of Object-Centric Abstractions for High-Level Planning

1 Jan 2021

Such representations can immediately be transferred between tasks that share the same types of objects, resulting in agents that require fewer samples to learn a model of a new task.

MINECRAFT

Machine Learning Prediction of Gamer's Private Networks

7 Dec 2020

Online games are a massive entertainment market and network latency is a key aspect of a player's competitive edge.

MINECRAFT

Predicting Human Strategies in Simulated Search and Rescue Task

15 Nov 2020

In our efforts to model the rescuer's mind, we begin with a simple simulated search and rescue task in Minecraft with human participants.

MINECRAFT

Explaining Differences in Classes of Discrete Sequences

6 Nov 2020

For example, psychologists are less interested in having a model that predicts human behavior with high accuracy and more concerned with identifying differences between actions that lead to divergent human behavior.

MINECRAFT

Task Scoping: Building Goal-Specific Abstractions for Planning in Complex Domains

17 Oct 2020

A generally intelligent agent requires an open-scope world model: one rich enough to tackle any of the wide range of tasks it may be asked to solve over its operational lifetime.

MINECRAFT

Generating Instructions at Different Levels of Abstraction

8 Oct 2020

When generating technical instructions, it is often convenient to describe complex objects in the world at different levels of abstraction.

MINECRAFT