CONTROLLING REINFORCEMENT LEARNING AGENTS USING GEOMETRIC POLICY COMPOSITION

• Main Authors: DABNEY, William Clinton, MUNOS, Remi, BORSA, Diana Luiza, THAKOOR, Shantanu Yogeshraj, DA MOTTA SALLES BARRETO, Andre, ROWLAND, Mark Daniel
• Format: Patent
• Language: English; French
• Published: 03.08.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; PHYSICS

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for controlling a reinforcement learning agent in an environment. One of the methods may include maintaining data specifying a base policy set comprising a plurality of base policies for controlling th...