Patent Applications by DeepMind Technologies Limited on June 26th, 2025

DeepMind Technologies Limited: 4 patent applications

DeepMind Technologies Limited has applied for patents in the areas of G06N3/092 (Reinforcement learning, 2), G06N3/084 (Backpropagation, e.g. using gradient descent, 1), G06N3/096 (Transfer learning, 1)

With keywords such as: system, learning, computer, systems, methods, training, using, machine, control, program in patent application abstracts.

Top Inventors:

Neil Charles Rabinowitz of St. Albans GB (1 patents)
Nicholas Andrew Roy of London GB (1 patents)
Junkyung Kim of London GB (1 patents)
Avishkar Ajay Bhoopchand of London GB (1 patents)
Adrian Ashley Collister of St Albans GB (1 patents)

Patent Applications by DeepMind Technologies Limited

20250209331. MACHINE LEARNING SYSTEMS COUNTERFACTUAL INTERVENTIONS (DeepMind Technologies Limited)

Abstract: systems, methods, and computer program, for training and using a machine learning system to control an agent to perform a task. the machine learning system is trained using counterfactual internal states so that it can provide an output that explains the behavior of the system in causal terms e.g. in terms of aspects of its environment that cause the system to select particular actions for the agent.

20250209337. AGENT CONTROL THROUGH CULTURAL TRANSMISSION (DeepMind Technologies Limited)

Abstract: methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for controlling agents. in particular, an agent can be controlled using a policy neural network that has been trained to allow the agent to achieve cultural transmission after training.

20250209338. EXPLORATION BOOTSTRAPPED PREDICTION (DeepMind Technologies Limited)

Abstract: an iterative method is proposed to train an action selection system of a reinforcement learning system, based on a reward function which defines a reward value for each action. the reward value includes an intrinsic reward term generated based on the outputs of two encoder models: an online encoder model and a target encoder model. the online encoder model is iteratively trained based on a loss function, and the target encoder model is updated to bring it closer to the online encoder model.

20250209340. INTRA-AGENT SPEECH FACILITATE TASK LEARNING (DeepMind Technologies Limited)

Abstract: systems, methods, and computer programs for learning to control an embodied agent to perform tasks. the techniques use internal, “intra-agent” speech when learning, and are thus able to perform tasks involving new objects without any direct experience of interacting with those objects, i.e. zero-shot. implementations of the techniques use an image captioning neural network system to generate natural language captions used when training an action selection neural network system.