Fast exploration and learning of latent graphs with aliased observations

Add code
Mar 21, 2023
Miguel Lazaro-Gredilla, Ishan Deshpande, Sivaramakrishnan Swaminathan, Meet Dave, Dileep George

Figure 1 for Fast exploration and learning of latent graphs with aliased observations
Figure 2 for Fast exploration and learning of latent graphs with aliased observations
Figure 3 for Fast exploration and learning of latent graphs with aliased observations
Figure 4 for Fast exploration and learning of latent graphs with aliased observations

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon

Consider this scenario: an agent navigates a latent graph by performing actions that take it from one node to another. The chosen action determines the probability distribution over the next visited node. At each node, the agent receives an observation, but this observation is not unique, so it does not identify the node, making the problem aliased. The purpose of this work is to provide a policy that approximately maximizes exploration efficiency (i.e., how well the graph is recovered for a given exploration budget). In the unaliased case, we show improved performance w.r.t. state-of-the-art reinforcement learning baselines. For the aliased case we are not aware of suitable baselines and instead show faster recovery w.r.t. a random policy for a wide variety of topologies, and exponentially faster recovery than a random policy for challenging topologies. We dub the algorithm eFeX (from eFficient eXploration).

* v2: Added extra figure and fixed typos  
View paper onarxiv iconopen_review iconOpenReview

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon