Page 251 of 522
1 249 250 251 252 253 522

How undesired goals can arise with correct rewards

As we build increasingly advanced artificial intelligence (AI) systems, we want to make sure they don’t pursue undesired goals. Such behaviour in an AI agent is often the result of specification gaming – exploiting a poor choice of what they are rewarded for. In our latest paper, we explore a more subtle mechanism by which AI systems may unintentionally learn to pursue undesired goals: goal misgeneralisation (GMG). GMG occurs when a system's capabilities generalise successfully but its goal does not generalise as desired, so the system competently pursues the wrong goal. Crucially, in contrast to specification gaming, GMG can occur even when the AI system is trained with a correct specification.

How undesired goals can arise with correct rewards

As we build increasingly advanced artificial intelligence (AI) systems, we want to make sure they don’t pursue undesired goals. Such behaviour in an AI agent is often the result of specification gaming – exploiting a poor choice of what they are rewarded for. In our latest paper, we explore a more subtle mechanism by which AI systems may unintentionally learn to pursue undesired goals: goal misgeneralisation (GMG). GMG occurs when a system's capabilities generalise successfully but its goal does not generalise as desired, so the system competently pursues the wrong goal. Crucially, in contrast to specification gaming, GMG can occur even when the AI system is trained with a correct specification.

How undesired goals can arise with correct rewards

As we build increasingly advanced artificial intelligence (AI) systems, we want to make sure they don’t pursue undesired goals. Such behaviour in an AI agent is often the result of specification gaming – exploiting a poor choice of what they are rewarded for. In our latest paper, we explore a more subtle mechanism by which AI systems may unintentionally learn to pursue undesired goals: goal misgeneralisation (GMG). GMG occurs when a system's capabilities generalise successfully but its goal does not generalise as desired, so the system competently pursues the wrong goal. Crucially, in contrast to specification gaming, GMG can occur even when the AI system is trained with a correct specification.

How undesired goals can arise with correct rewards

As we build increasingly advanced artificial intelligence (AI) systems, we want to make sure they don’t pursue undesired goals. Such behaviour in an AI agent is often the result of specification gaming – exploiting a poor choice of what they are rewarded for. In our latest paper, we explore a more subtle mechanism by which AI systems may unintentionally learn to pursue undesired goals: goal misgeneralisation (GMG). GMG occurs when a system's capabilities generalise successfully but its goal does not generalise as desired, so the system competently pursues the wrong goal. Crucially, in contrast to specification gaming, GMG can occur even when the AI system is trained with a correct specification.

How undesired goals can arise with correct rewards

As we build increasingly advanced artificial intelligence (AI) systems, we want to make sure they don’t pursue undesired goals. Such behaviour in an AI agent is often the result of specification gaming – exploiting a poor choice of what they are rewarded for. In our latest paper, we explore a more subtle mechanism by which AI systems may unintentionally learn to pursue undesired goals: goal misgeneralisation (GMG). GMG occurs when a system's capabilities generalise successfully but its goal does not generalise as desired, so the system competently pursues the wrong goal. Crucially, in contrast to specification gaming, GMG can occur even when the AI system is trained with a correct specification.

How undesired goals can arise with correct rewards

As we build increasingly advanced artificial intelligence (AI) systems, we want to make sure they don’t pursue undesired goals. Such behaviour in an AI agent is often the result of specification gaming – exploiting a poor choice of what they are rewarded for. In our latest paper, we explore a more subtle mechanism by which AI systems may unintentionally learn to pursue undesired goals: goal misgeneralisation (GMG). GMG occurs when a system's capabilities generalise successfully but its goal does not generalise as desired, so the system competently pursues the wrong goal. Crucially, in contrast to specification gaming, GMG can occur even when the AI system is trained with a correct specification.

How undesired goals can arise with correct rewards

As we build increasingly advanced artificial intelligence (AI) systems, we want to make sure they don’t pursue undesired goals. Such behaviour in an AI agent is often the result of specification gaming – exploiting a poor choice of what they are rewarded for. In our latest paper, we explore a more subtle mechanism by which AI systems may unintentionally learn to pursue undesired goals: goal misgeneralisation (GMG). GMG occurs when a system's capabilities generalise successfully but its goal does not generalise as desired, so the system competently pursues the wrong goal. Crucially, in contrast to specification gaming, GMG can occur even when the AI system is trained with a correct specification.

How undesired goals can arise with correct rewards

As we build increasingly advanced artificial intelligence (AI) systems, we want to make sure they don’t pursue undesired goals. Such behaviour in an AI agent is often the result of specification gaming – exploiting a poor choice of what they are rewarded for. In our latest paper, we explore a more subtle mechanism by which AI systems may unintentionally learn to pursue undesired goals: goal misgeneralisation (GMG). GMG occurs when a system's capabilities generalise successfully but its goal does not generalise as desired, so the system competently pursues the wrong goal. Crucially, in contrast to specification gaming, GMG can occur even when the AI system is trained with a correct specification.

Mobile Industrial Robots and AutoGuide Mobile Robots Merge to Simplify Automation of Customers’ Internal Logistics with Full Portfolio of Safe, Collaborative AMRs

Under the Mobile Industrial Robot (MiR) name and led by Walter Vahey, the two Teradyne companies become a single supplier of autonomous mobile robots (AMRs), accelerating technology development and market leadership worldwide

Discovering novel algorithms with AlphaTensor

In our paper, published today in Nature, we introduce AlphaTensor, the first artificial intelligence (AI) system for discovering novel, efficient, and provably correct algorithms for fundamental tasks such as matrix multiplication. This sheds light on a 50-year-old open question in mathematics about finding the fastest way to multiply two matrices. This paper is a stepping stone in DeepMind’s mission to advance science and unlock the most fundamental problems using AI. Our system, AlphaTensor, builds upon AlphaZero, an agent that has shown superhuman performance on board games, like chess, Go and shogi, and this work shows the journey of AlphaZero from playing games to tackling unsolved mathematical problems for the first time.

Discovering novel algorithms with AlphaTensor

In our paper, published today in Nature, we introduce AlphaTensor, the first artificial intelligence (AI) system for discovering novel, efficient, and provably correct algorithms for fundamental tasks such as matrix multiplication. This sheds light on a 50-year-old open question in mathematics about finding the fastest way to multiply two matrices. This paper is a stepping stone in DeepMind’s mission to advance science and unlock the most fundamental problems using AI. Our system, AlphaTensor, builds upon AlphaZero, an agent that has shown superhuman performance on board games, like chess, Go and shogi, and this work shows the journey of AlphaZero from playing games to tackling unsolved mathematical problems for the first time.

Discovering novel algorithms with AlphaTensor

In our paper, published today in Nature, we introduce AlphaTensor, the first artificial intelligence (AI) system for discovering novel, efficient, and provably correct algorithms for fundamental tasks such as matrix multiplication. This sheds light on a 50-year-old open question in mathematics about finding the fastest way to multiply two matrices. This paper is a stepping stone in DeepMind’s mission to advance science and unlock the most fundamental problems using AI. Our system, AlphaTensor, builds upon AlphaZero, an agent that has shown superhuman performance on board games, like chess, Go and shogi, and this work shows the journey of AlphaZero from playing games to tackling unsolved mathematical problems for the first time.
Page 251 of 522
1 249 250 251 252 253 522