In recent studies, linear recurrent neural networks (LRNNs) have achieve...
Unlike recurrent models, conventional wisdom has it that Transformers ca...
Length extrapolation is a desirable property that permits training a
tra...
While deep generative models have succeeded in image processing, natural...
Relative positional embeddings (RPE) have received considerable attentio...
Off-policy Actor-Critic algorithms have demonstrated phenomenal experime...
Reinforcement learning is well-studied under discrete actions. Integer
a...
We introduce PowerGym, an open-source reinforcement learning environment...
Model-based Reinforcement Learning has shown considerable experimental
s...
Model-based reinforcement learning (MBRL) aims to learn a dynamic model ...