Timezone: »

Improving PAC Exploration Using the Median Of Means
Jason Pazis · Ronald Parr · Jonathan How

Mon Dec 05 09:00 AM -- 12:30 PM (PST) @ Area 5+6+7+8 #69

We present the first application of the median of means in a PAC exploration algorithm for MDPs. Using the median of means allows us to significantly reduce the dependence of our bounds on the range of values that the value function can take, while introducing a dependence on the (potentially much smaller) variance of the Bellman operator. Additionally, our algorithm is the first algorithm with PAC bounds that can be applied to MDPs with unbounded rewards.

Author Information

Jason Pazis (MIT)
Ronald Parr (Duke University)
Jonathan How (MIT)

More from the Same Authors