Reinforcement Learning with Options and State Representation

no code implementations • 16 Mar 2024 • Ayoub Ghriss, Masashi Sugiyama, Alessandro Lazaric

The current thesis aims to explore the reinforcement learning field and build on existing methods to produce improved ones to tackle the problem of learning in high-dimensional and complex environments.

Decision Making Hierarchical Reinforcement Learning +1

Sentiment-Aware Automatic Speech Recognition pre-training for enhanced Speech Emotion Recognition

no code implementations • 27 Jan 2022 • Ayoub Ghriss, Bo Yang, Viktor Rozgic, Elizabeth Shriberg, Chao Wang

We pre-train SER model simultaneously on Automatic Speech Recognition (ASR) and sentiment classification tasks to make the acoustic ASR model more ``emotion aware''.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +5