Browsing Year-2021 by Author "Anand, Saket (Advisor)"

Now showing items 1-2 of 2

Geometry driven disentangled representation learning

Gupta, Devansh; Chhabra, Parth; Anand, Saket (Advisor); Kalyanaraman, Kaushik (Advisor) (2021-11)

In machine learning, disentangling factors of variation lead to robust latent space representations and improve the efficacy of various downstream tasks like classification, prediction etc. Disentangling representations ...
State representation learning for reinforcement learning setting

Thakral, Shubham; Anand, Saket (Advisor); Kaul, Sanjit Krishnan (Advisor) (IIIT- Delhi, 2021-06)

Most of the Reinforcement Learning(RL) tasks in today's world involve high dimensional data. Training deep reinforcement learning based models is already a very challenging task and varies lot with the choice of hyper ...

Now showing items 1-2 of 2

Search Repository