Interface administrators, Administrators (Semantic MediaWiki), Curators (Semantic MediaWiki), Editors (Semantic MediaWiki), Suppressors, Administrators
7,785
edits
Gym Retro: Difference between revisions
no edit summary
PauloPacheco (talk | contribs) (Created page with "Gym Retro is a platform for Reinforcement Learning (RL) research on games developed by OpenAI and released in 2018. It turns retro video games into Gym environments, using different emulators that support the Libretro API for each system. This makes it easy to add new emulators. A tool to add new games was also made available. <ref name="”1”"> OpenAI (2018). Gym Retro. OpenAI. https://openai.com/blog/gym-retro/</ref> <ref name="”2”"> OpenAI. Retr...") |
No edit summary |
||
| (One intermediate revision by the same user not shown) | |||
| Line 19: | Line 19: | ||
Between April 5th and June 5th of 2018, OpenAI held a contest using the Sonic The Hedgehog™ series of games for SEGA Genesis to have participants create "the best agent for playing custom levels of the Sonic games — without having access to those levels during development." <ref name="”6”"> OpenAI (2018). OpenAI Retro Contest. Retro Contest. https://contest.openai.com/2018-1/</ref> It was a way of measuring the ability of an RL algorithm to generalize based on previous experience. This contest used Gym Retro, providing a test for algorithms on previously unseen video game levels. <ref name="”4”"></ref> | Between April 5th and June 5th of 2018, OpenAI held a contest using the Sonic The Hedgehog™ series of games for SEGA Genesis to have participants create "the best agent for playing custom levels of the Sonic games — without having access to those levels during development." <ref name="”6”"> OpenAI (2018). OpenAI Retro Contest. Retro Contest. https://contest.openai.com/2018-1/</ref> It was a way of measuring the ability of an RL algorithm to generalize based on previous experience. This contest used Gym Retro, providing a test for algorithms on previously unseen video game levels. <ref name="”4”"></ref> | ||
The Retro Contest gave the participants a training set of levels from the Sonic The Hedgehog™ series and OpenAI evaluated the submissions on a test set of custom levels created for the contest. <ref name="”4”"></ref> | The Retro Contest gave the participants a training set of levels from the Sonic The Hedgehog™ series and OpenAI evaluated the submissions on a [[test set]] of custom levels created for the contest. <ref name="”4”"></ref> | ||
OpenAI provided an overview of the contest where participants had to 1) train or script the agent to play Sonic; 2) submit the agent as a Docker container; and then agents received their 3) evaluation on a set of secret test levels; and 5) the agent's score appeared on the leaderboard. <ref name="”6”"></ref> | OpenAI provided an overview of the contest where participants had to 1) train or script the agent to play Sonic; 2) submit the agent as a Docker container; and then agents received their 3) evaluation on a set of secret test levels; and 5) the agent's score appeared on the leaderboard. <ref name="”6”"></ref> | ||