Graying the black box: Understanding DQNs — mentioned by blueboo

Thu, 07 Sep 2023 14:37:23 GMT

There’s no helping the incurious, but there are indeed reams of explorations unto weights and their explanations. One of my personal favourites is Zeiler and Fergus https://arxiv.org/abs/1311.2901 Tom Zahavy’s “Greying the black box” on deep RL comes to mind too https://arxiv.org/abs/1602.02658 OpenAI has their Microscope tool for investigating individual neurons https://openai.com/research/microscope; more recently OpenAI shared research and tooling leveraging a powerful language model to explain a smaller model’s neurons. https://openai.com/research/language-models-can-explain-neur... For a…

Paper and discussion history. A mention is not an endorsement.

Graying the black box: Understanding DQNs — mentioned by visarga

Mon, 09 May 2016 04:15:58 GMT

I read a paper [1] about visualizing the Deep Q-Network used for playing Atari games. They map to 2D the game state and then colorize it by the Q scores. As a result they could visualize the strategy and observe how it is hierarchically organized in clusters containing sub-clusters. They could show regions associated with initial and termination rules. This method can be used to map out a game strategy and to focus on specific regions. [1] Graying the black box: Understanding DQNs - https://arxiv.org/pdf/1602.02658.pdf

Paper and discussion history. A mention is not an endorsement.

Graying the black box: Understanding DQNs · HackerPapers discussions

Graying the black box: Understanding DQNs — mentioned by blueboo

Graying the black box: Understanding DQNs — mentioned by visarga