Dream to Control: Learning Behaviors by Latent Imagination We present Dreamer, a reinforcement learning agent that solves long-horizon tasks from images purely by latent imagination We efficiently learn behaviors by propagating analytic gradients of learned state values back through trajectories imagined in the compact state space of a learned world model
Mastering Diverse Domains through World Models - GitHub python dreamerv3 main py \ --logdir ~ logdir dreamer {timestamp} \ --configs crafter \ --run train_ratio 32 To reproduce results, train on the desired task using the corresponding config, such as --configs atari --task atari_pong View results: