In order to express desired (SRL) architecture for safe control in Radio Access Network (RAN) specifications to the network into consideration, LTL is used applications. In our automated tool, a user can select a high-level (see [2, 10, 12, 13]), due to the fact that it provides a powerful mathematical safety specifications expressed in Linear Temporal Logic (LTL) to formalism for such purpose. Our proposed demonstration shield an RL agent running in a given cellular network with aim exhibits the following attributes: of optimizing network performance, as measured through certain (1) a general automatic framework from LTL specification user Key Performance Indicators (KPIs). In the proposed architecture, input to the derivation of the policy that fulfills it; at the same network safety shielding is ensured through model-checking techniques time, blocking the control actions that violate the specification; over combined discrete system models (automata) that are (2) novel system dynamics abstraction to companions Markov Decision abstracted through reinforcement learning. We demonstrate the Processes (MDP) which is computationally efficient; user interface (UI) helping the user set intent specifications to the (3) UI development that allows the user to graphically access all architecture and inspect the difference in allowed and blocked actions.

Deep Reinforcement Learning (deep RL) has made several breakthroughs in recent years in applications ranging from complex control tasks in unmanned vehicles to game playing. Despite their success, deep RL still lacks several important capacities of human intelligence, such as transfer learning, abstraction and interpretability. Deep Symbolic Reinforcement Learning (DSRL) seeks to incorporate such capacities to deep Q-networks (DQN) by learning a relevant symbolic representation prior to using Q-learning. In this paper, we propose a novel extension of DSRL, which we call Symbolic Reinforcement Learning with Common Sense (SRL CS), offering a better balance between generalization and specialization, inspired by principles of common sense when assigning rewards and aggregating Q-values. Experiments reported in this paper show that SRL CS learns consistently faster than Q-learning and DSRL, achieving also a higher accuracy. In the hardest case, where agents were trained in a deterministic environment and tested in a random environment, SRL CS achieves nearly 100% average accuracy compared to DSRL's 70% and DQN's 50% accuracy. To the best of our knowledge, this is the first case of near perfect zero-shot transfer learning using Reinforcement Learning.