On the Verge of Solving Rocket League using Deep Reinforcement Learning and Sim-to-sim Transfer

05/10/2022
by   Marco Pleines, et al.
14

Autonomously trained agents that are supposed to play video games reasonably well rely either on fast simulation speeds or heavy parallelization across thousands of machines running concurrently. This work explores a third way that is established in robotics, namely sim-to-real transfer, or if the game is considered a simulation itself, sim-to-sim transfer. In the case of Rocket League, we demonstrate that single behaviors of goalies and strikers can be successfully learned using Deep Reinforcement Learning in the simulation environment and transferred back to the original game. Although the implemented training simulation is to some extent inaccurate, the goalkeeping agent saves nearly 100 scores in about 75 able to generalize to the target domain of Rocket League.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset