Using Eligibility Traces to Find the Best Memoryless Policy in Partially Observable MDPs. John Loch, Satinder Singh.

1. Basically uses eligibility traces to find policies in POMDPs; previous methods mainly used memory to estimate state, which gets computationally expensive
2. Results are relevant to: “POMDPs that have good memoryless policies, i.e., on problems in which there may well be very poor observability but there also exists a mapping from the agent’s immediate observations to actions that yield near-optimal return.”
3. Paper is almost entirely empirical results