In the traditional federated learning setting, a central server coordina...
Actor-critic (AC) methods are ubiquitous in reinforcement learning. Alth...
We consider the problem of approximating the stationary distribution of ...
Transfer in Reinforcement Learning (RL) refers to the idea of applying
k...
In many real-world applications, we want to exploit multiple source data...
Deep neural networks are known to suffer the catastrophic forgetting pro...
The objective of transfer reinforcement learning is to generalize from a...