NetHack: Learning Environment
Jul 18, 2020
Speakers
Heinrich Küttler
Speaker · 0 followers
Nantas Nardelli
Speaker · 0 followers
Alexander H. Miller
Speaker · 0 followers
Roberta Raileanu
Speaker · 0 followers
Marco Selvatici
Speaker · 0 followers
Edward Grefenstette
Speaker · 0 followers
Tim Rocktäschel
Speaker · 0 followers
About
Progress in Reinforcement Learning (RL) algorithms goes hand-in-hand with the development of challenging environments that test the limits of current methods. While existing RL environments are either sufficiently complex or based on fast simulation, they are rarely both these things. In this talk, I present the NetHack Learning Environment (NLE), a scalable, procedurally generated, stochastic, rich, and challenging environment for RL research based on the popular single-player terminal-based rogue like game, NetHack. We argue that NetHack is sufficiently complex to drive long-term research on problems such as exploration, planning, skill acquisition, and language-conditioned RL, while dramatically reducing the computational resources required to gather a large amount of experience. We compare NLE and its task suite to existing alternatives, and discuss why it is an ideal medium for testing the robustness and systematic generalization of RL agents. We demonstrate empirical success for early stages of the game using a distributed deep RL baseline and Random Network Distillation exploration, alongside qualitative analysis of various agents trained in the environment. NLE is open-source at https://github.com/facebookresearch/nle .Progress in Reinforcement Learning (RL) algorithms goes hand-in-hand with the development of challenging environments that test the limits of current methods. While existing RL environments are either sufficiently complex or based on fast simulation, they are rarely both these things. In this talk, I present the NetHack Learning Environment (NLE), a scalable, procedurally generated, stochastic, rich, and challenging environment for RL research based on the popular single-player terminal-based r…
Categories
AI & Data Science
Category · 10.8k presentations
App & Game Development
Category · 954 presentations
Software & Programming
Category · 1k presentations
About ICML 2020
The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Optimal Statistical Guaratees for Adversarially Robust Gaussian Classification
Watch later
Chen Dan, …
Submodular Optimization: From Discrete to Continuous and Back - Part II
Watch later
Frequency Bias in Neural Networks for Input of Non-Uniform Density
Watch later
Ronen Basri, …
The Effect of Natural Distribution Shift on Question Answering Models
Watch later
John Miller, …