Search Results for author:
Found 3 papers, 0 papers with code
BET: Explaining Deep Reinforcement Learning through The Error-Prone Decisions
To address this issue, we propose a novel self-interpretable structure, named Backbone Extract Tree (BET), to better explain the agent's behavior by identify the error-prone states.
Fidelity-Induced Interpretable Policy Extraction for Reinforcement Learning
We then design a fidelity-induced mechanism by integrate a fidelity measurement into the reinforcement learning feedback.
Content-based similar document image retrieval using fusion of CNN features
Rapid increase of digitized document give birth to high demand of document image retrieval.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
