Transfer Learning(TL) has been shown to significantly accelerate the convergence of a reinforcement learning process. TL is the process of reusing learned information across tasks. Information is shared between a source and a target task. Previous work has required that the target task wait until the source task has finished learning before transferring in-formation. The execution of the source task prior to the target task considerably extends the time required for the target task to com-plete. This paper proposes a novel approach allowing both source and target task to learn in parallel. This allows the transfer to be bi-directional, so processes can act as both source and target simultaneously. This, in consequence, allows tasks to learn from each other’s experiences and thereby reduces the learning time required. The proposed ap-proach is evaluated on a multi-agent smart-grid scenario. 1.

Demand-Side Management (DSM) refers to programs that aim to control the energy consumption at the customer side of the meter. Different techniques have been proposed to achieve this. Perhaps the most popular techniques are those based on smart pricing (e.g., critical-peak pricing, real-time pricing). The idea, in a nutshell, is to encourage end users to shift their load consumption based on the price at a par-ticular time (e.g., the higher the price, the less number of electric appliances are expected to be turned on). Motivated by these techniques (e.g., a strong positive correlation be-tween the number of appliances being used and the electric-ity cost), we propose the use of an stochastic evolutionary-based optimisation technique, Evolutionary Algorithms, to automatically generate optimal, or nearly optimal, solutions