A Instantaneous Regret Bound Conditioned on the event that (8) in Lemma 1 holds (with probability 1 δ), it follows that c

From (18), (19), and (20), we obtain (9), (10), and (11), respectively. We prove the following Lemma 4 which is then used to prove Lemma 5. Lemma 3 follows from Lemma 5. Lemma 4. Let W Thus, Lemma 5 implies Lemma 3. Let us consider V -TS that selects a single query at each BO iteration (Algorithm 3). The simulation returns the location of a pushed object given the robot's location and the pushing duration, i.e., There are 30 initial observations, i.e., | D