Ask a question below.
Published answers will appear here.
Cool paper from @LarsvanderLaan3 and @nathankallus: you can use MLE to estimate density-ratio in MDP w/o completeness. Usually you need latter b/c bellman op and projection contract in diff geometries, but in this case it's both KL. Very cool insight. https://arxiv.org/abs/2607.05375
on side note, the fun of working in RL theory is that results like this are still discovered from time to time, where a few lines explain (to experts) significance + proof machinery, and we are like "how come we didn't realize this before" https://twitter.com/nanjiang_cs/status/2076464743594807506
Cool paper from @LarsvanderLaan3 and @nathankallus: you can use MLE to estimate density-ratio in MDP w/o completeness. Usually you need latter b/c bellman op and projection contract in diff geometries, but in this case it's both KL. Very cool insight. https://arxiv.org/abs/2607.05375
on side note, the fun of working in RL theory is that results like this are still discovered from time to time, where a few lines explain (to experts) significance + proof machinery, and we are like "how come we didn't realize this before" https://twitter.com/nanjiang_cs/status/2076464743594807506
Ask a question below.
Published answers will appear here.