From c59fa660939ca09cb2063b0f6b6dc3fd826c2f1f Mon Sep 17 00:00:00 2001 From: Brian Robinson Date: Tue, 28 Jan 2025 15:50:39 -0600 Subject: [PATCH] Update glossary.mdx Added 'reinforcement learning' and 'deep reinforcement learning' to the glossary. --- units/en/unit1/glossary.mdx | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/units/en/unit1/glossary.mdx b/units/en/unit1/glossary.mdx index ed2b0aaa..48a916bf 100644 --- a/units/en/unit1/glossary.mdx +++ b/units/en/unit1/glossary.mdx @@ -2,6 +2,14 @@ This is a community-created glossary. Contributions are welcome! +### Reinforcement Learning + +A trial-and-error learning paradigm in which an agent learns an optimal policy for taking an action given an observation about the state of its environment, in order to maximize future discounted rewards. + +### Deep Reinforcement Learning + +Reinforcement learning in which the policy or value function to be trained (i.e. the agent's brain) is instantiated as a deep neural network. + ### Agent An agent learns to **make decisions by trial and error, with rewards and punishments from the surroundings**.