Extended Data Fig. 5: Training progress. | Nature

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript. Advertisement From: Magnetic control of tokamak plasmas through deep reinforcement learning Episodic reward for the deterministic policy smoothed across 20 episodes with parameter variations enabled, in which 100 means that all objectives are perfectly met.  a comparison of the learning curve for the capability benchmark (as shown in Fig. 2) using our asymmetric actor-critic versus a symmetric actor-critic, in which the critic is using the same real-time-capable feedforward network as the actor. In blue is the performance with the default critic of 718,337 parameters. In orange, we show the symmetric version, in which the

saved by

• Clementine Yang