Archives for Atari games

04 Apr

How DeepMind’s Agent57 Outperformed Humans In 57 Atari Games

image-11609
image-11609

In a paper published by DeepMind, a team of scientists from Alphabet’s UK-based research division has claimed that Agent57 – the first deep reinforcement learning agent – has outperformed humans on all 57 Atari 2600 games in the Arcade Learning Environment data set.  Agent57 combines an algorithm to efficiently explore a meta controller which adapts…

The post How DeepMind’s Agent57 Outperformed Humans In 57 Atari Games appeared first on Analytics India Magazine.

28 Feb

Generalization in Reinforcement Learning – Exploration vs Exploitation

In Reinforcement learning, the generalization of the agents is benchmarked on the environments they have been trained on. In a supervised learning setting, this would mean testing the model using the training dataset. OpenAI has open-sourced Procgen-benchmark emphasizing the generalization for RL agents as they struggle to generalize in new environments. Procgen consists of 16…

The post Generalization in Reinforcement Learning – Exploration vs Exploitation appeared first on Analytics India Magazine.