[Feature Request] Extend TDLambdaEstimator with QLambdaEstimator

[roger-creus]

Motivation

Attempting to implement Parallel Q Networks (online DQN without replay buffer or target networks). Uses QLambda returns.

Solution

TDLambdaEstimator expects state_value keys but we would now need action_value keys

Checklist

• [x] I have checked that there is no similar issue in the repo (required)