I was fortunate to come across a fascinating paper on C-Learning: Learning to Achieve Goals via Recursive Classification (Eysenbach, et. al) from ICLR 2021. I truly believe that the ideas presented in the paper are unique and valuable for many researchers in reinforcement learning. …
How do we capture position and order of data?
Key Intuition Behind Positional Encodings
Introduction:
Understanding the position and order is crucial in many tasks that involve sequences. Positional encoding play a crucial role in the widely known Transformer model (Vaswani, et al. 2019) because the architecture doesn’t naturally include the information about order of the…
