Image Credit: Facebook Research

Ik ben onlangs begonnen met een nieuwe nieuwsbrief focus op AI-onderwijs en heeft al meer dan 50,000 abonnees​ TheSequence is een no-BS (wat betekent geen hype, geen nieuws, enz.) AI-gerichte nieuwsbrief die 5 minuten duurt om te lezen. Het doel is om u op de hoogte te houden van machine learning-projecten, research papers en concepten. Probeer het alsjeblieft door je hieronder te abonneren:

Reinforcement learning(RL) has been at the center of some of the most impressive achievements in artificial intelligence(AI) in the last decade. From DeepMind’s famous AlphaGo to milestones in games such as StarCraft II, Dota 2 or Minecraft, RL remains one of the fastest growing areas in the deep learning space. Despite all its success, Facebook AI Research(FAIR) believes that RL needs to be pushed to new levels and, for that, they are turning their attention to a new game: NetHack.

The FAIR team just launched the NetHack Challenge as part of the upcoming NeurIPS 2021 competition. The objective is to test new RL ideas using a one of the toughest game environments in the world.

NetHack and RL

 
NetHack is a traditional dungeon game that has been under development since the 1980s and its incredibly tough to master for new players. For once, mistakes in NetHack have a disproportional cost. Once a player dies, the game starts from scratch in a completely different dungeon. To complete the game successfully, a player needs to execute about 25–50x more steps than in StarCraft. Additionally, the solution to many problems in NetHack require creativity and consulting external knowledge sources which results incredibly hard to model from a strategic standpoint.

Image Credit: Facebook Research

Image Credit: Facebook Research

From the RL perspective, NetHack presents a unique set of challenges:

• Agents cannot reset the environment so optimization methods such as Monte Carlo Tree Search are useless in that type of setting.
• Exploration is even more important given the partial completeness of the environment.
• The high variability of changes in the environment requires rapidly adaptative RL techniques.

Among other things, the NetHack challenge should bring a new set of RL methods that can operate in highly complex environments in which errors have a significant cost. This should help advance research in areas such as navigation or many industrial environments that share some macro-characteristics with NetHack. Can’t wait to see the first wave of submissions.

 
ORIGINELE. Met toestemming opnieuw gepost.

Zie ook:

• 10 Real-Life toepassingen van Reinforcement Learning
• Aan de slag met versterkend leren
• DeepMind wil een van de belangrijkste algoritmen in machine learning opnieuw vormgeven