A catastrophic bifurcation in non-linear dynamical systems, called crisis, often leads to their convergence to an undesirable non-chaotic state after some initial chaotic transients. Preventing such behavior has been quite challenging. We demonstrate that deep Reinforcement Learning (RL) is able to restore chaos in a transiently chaotic regime of the Lorenz system of equations. Without requiring any a priori knowledge of the underlying dynamics of the governing equations, the RL agent discovers an effective strategy for perturbing the parameters of the Lorenz system such that the chaotic trajectory is sustained. We analyze the agent's autonomous control-decisions and identify and implement a simple control-law that successfully restores chaos in the Lorenz system. Our results demonstrate the utility of using deep RL for controlling the occurrence of catastrophes in non-linear dynamical systems.