AI beats self, learns to play Atari game 6000 times faster than before
AI beats self, learns to play Atari game 6000 times faster than before
AI beats self, learns to play Atari game 6000 times faster than before
By Loukia Papadopoulos
March 12, 2023
Summary
Now a team from Carnegie Mellon University has devised a way to aid reinforcement learning algorithms learn much faster by combining them with a language model that can read instruction manuals, according to a report published on Friday by Singularity Hub.
They have been successful in teaching an AI to play a challenging Atari video game thousands of times faster than a model developed by DeepMind.
"Our work is the first to demonstrate the possibility of a fully-automated reinforcement learning framework to benefit from an instruction manual for a widely studied game," said Yue Wu, who led the research.
"We have been conducting experiments on other more complicated games like Minecraft, and have seen promising results. We believe our approach should apply to more complex problems." Summarizing key information The team began by training a language model to extract and summarize key information from the game's official instruction manual.
The resulting answers were then used to create additional rewards for the reinforcement algorithm and fed into a well-established reinforcement learning algorithm to help it learn the game faster.
To assess their approach, the researchers tested it on Skiing 6000, a game where the leading AI had to run through 80 billion frames of the game to achieve comparable performance to a human.
Read and Reward speeds up RL algorithm son Atari games by reading manuals released by the Atari game developers.
Reference
Papadopoulos, L. (2023, March 12). Ai Beats Self, learns to play Atari Game 6000 times faster than before. Interesting Engineering. Retrieved April 3, 2023, from https://interestingengineering.com/innovation/ai-atari-6000-times-faster