Questions tagged [offline-reinforcement-learning]
The offline-reinforcement-learning tag has no usage guidance.
4
questions with no upvoted or accepted answers
1
vote
1
answer
108
views
Fit Q Evaluation in offline reinforcement learning
I am working on a PyTorch implementation of Implicit Q-Learning (IQL) (paper), given a dataset $\mathcal D = \left\{ (\mathbf s_i, \mathbf a_i, \mathbf s_i', r_i ) \right\}$ of transitions. I think I ...
- 111
0
votes
0
answers
19
views
Offline CartPole on infinitely long line?
I am tentatively exploring some RL research that involves doing offline RL on a version of the Gymnasium CartPole where the cart can move on $\mathbb R$, as opposed to the standard version (see link) ...
- 111
0
votes
0
answers
34
views
How to evaluate the performance of off-line & model-free reinforcement leaning?
I'm currently studying on off-line reinforcement learning (RL) and trying to utilize it for medical data. Because it seemed hard to develop well-performing environment model, I decided to adopt model-...
- 1
0
votes
1
answer
240
views
Action selection in Batch-Constrained Deep Q-learning (BCQ)
For simplicity, let's consider the discrete version of BCQ where the paper and the code are available. In the line 5 of Algorithm 1 we have the following:
$$
a' = \text{argmax}_{a'|G_{\omega}(a', s')/\...
- 81