Neural Information Processing Systems http://nips.cc/

TheinterplayIv: k models Iu: p samples model) is ensemble.

Existing approaches to addressing shifts, such as concept drift adaptation, are limited by theirreason-agnosticnature.

The key challenge in making this connection is grounding the skills, so that each skill corresponds to a specific goal-conditioned policy. We start by recalling the definition of the discounted state occupancymeasure(Eq.3): p(st+=sg)=(1 γ) X On the second line, we havechanged the bounds of the summation to start at 0, and changed the terms inside the summation accordingly. On the third line, we applied linearity of expectation to movethesummation insidetheexpectation. Onthefourthline,weappliedlinearity ofexpectation again to move the term fort = 0 inside the expectation. Finally, we substituted the definition of rg(s,a)toobtainthedesiredresult. This result means that we are doing policy improvement with approximate Q-values.

We usethisideatoreinterpret aprior RLmethod asperforming contrastivelearning, and then use the idea to propose a much simpler method that achieves similar performance. Across arange ofgoal-conditioned RLtasks, wedemonstrate that contrastive RL methods achieve higher success rates than prior non-contrastive methods, including in the offline RL setting.

Neural Information Processing Systems http://nips.cc/