Skip to main content
21 votes

What is the relation between online (or offline) learning and on-policy (or off-policy) algorithms?

The concepts of on-policy vs off-policy and online vs offline are separate, but do interact to make certain combinations more feasible. When looking at this, it is worth also considering the ...
Neil Slater's user avatar
  • 32.7k
4 votes

Export trained model offline to be used by an application

Is it possible that I can train my data online (using any cloud provider) using a text classification model, and then export the model already trained (in the form of a script, I don't know how the ...
Neil Slater's user avatar
  • 32.7k
2 votes

Expectile regression in Implicit Q-Learning

Because $argmin_{m_\tau} E_{x\sim X} \left[L_2^\tau(x - m_\tau)\right]$ approximates $max_{x \in X} \hspace{0.1cm} x$, then $E_{(s,a,s')\sim \mathcal{D}}\left[\left(max_{a'\in \mathcal{A}\;s.t. \pi_\...
user118967's user avatar
1 vote

DQN with experience history to learn from already saved - which reward should I take?

More specifically than off-policy RL, you are looking at offline reinforcement learning techniques. In offline RL, all training data is known beforehand (stationary), which is in stark contrast to the ...
DeepQZero's user avatar
  • 1,424
1 vote

Offline/Batch Reinforcement Learning: when to stop training and what agent to select

We have deployed one project in the real world that uses offline RL algorithms. Evaluating the performance of a policy is indeed a very tricky problem. Unfortunately, most existing OPE method is not ...
Xianyuan Zhan's user avatar

Only top scored, non community-wiki answers of a minimum length are eligible