Sign in

Can Learned Optimization Make Reinforcement Learning Less Difficult?

By Alexander David Goldie and others
While reinforcement learning (RL) holds great potential for decision making in the real world, it suffers from a number of unique difficulties which often need specific consideration. In particular: it is highly non-stationary; suffers from high degrees of plasticity loss; and requires exploration to prevent premature convergence to local optima... Show more
July 9, 2024
=
0
Loading PDF…
Loading full text...
Similar articles
Loading recommendations...
=
0
x1
Can Learned Optimization Make Reinforcement Learning Less Difficult?
Click on play to start listening