5
$\begingroup$

This question can seem a little bit too broad, but I am wondering what are the current state-of-the-art works on meta reinforcement learning. Can you provide me with the current state-of-the-art in this field?

$\endgroup$
3
$\begingroup$

One of the most recent papers on meta-RL is meta-Q-learning This paper introduces Meta-Q-Learning (MQL), a new off-policy algorithm for meta-reinforcement learning (meta-RL). MQL builds upon three simple ideas.

  • Q-learning is competitive with state of the art meta-RL algorithms if given access to a context variable that is a representation of the past trajectory.

  • Using a multi-task objective to maximize the average reward across the training tasks is an effective method to meta-train RL policies.

  • past data from the meta-training replay buffer can be recycled to adapt the policy on a new task using off-policy updates

Experiments on standard continuous-control benchmarks suggest that MQL compares favorably with state of the art meta-RL algorithms

| improve this answer | |
$\endgroup$
  • 2
    $\begingroup$ Although the OP is apparently happy with your answer, is MQL the only SOTA work in meta RL? Maybe you could list other SOTA works, if you are aware of any other ;) $\endgroup$ – nbro Feb 8 at 11:43
  • $\begingroup$ I think that references to other work on meta-RL are present on the expermients part on the MQL paper, the list of cited works their is enough to have an overview of hte current current state-of-the-art, don't u agree on this ? $\endgroup$ – hola Feb 8 at 11:49
  • $\begingroup$ After having quickly skimmed through that paper, you're apparently right, but it would also be nice to see the names of other SOTA methods in your answer (but I won't force you). And thanks already for contributing and helping! $\endgroup$ – nbro Feb 8 at 11:55

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.