Reinforcement learning agents often forget details of the past, especially after delays or distractor tasks. Agents with common memory architectures struggle to recall and integrate across multiple timesteps of a past event, or even to recall the details of a single timestep that is followed by distractor tasks. To address these limitations, we propose a Hierarchical Chunk Attention Memory (HCAM), that helps agents to remember the past in detail. HCAM stores memories by dividing the past into chunks, and recalls by first performing high-level attention over coarse summaries of the chunks, and then performing detailed attention within only the most relevant chunks. An agent with HCAM can therefore mentally time-travel--remember past events in detail without attending to all intervening events.

Reinforcement learning agents often forget details of the past, especially after delays or distractor tasks. Agents with common memory architectures struggle to recall and integrate across multiple timesteps of a past event, or even to recall the details of a single timestep that is followed by distractor tasks. To address these limitations, we propose a Hierarchical Chunk Attention Memory (HCAM), that helps agents to remember the past in detail. HCAM stores memories by dividing the past into chunks, and recalls by first performing high-level attention over coarse summaries of the chunks, and then performing detailed attention within only the most relevant chunks. An agent with HCAM can therefore "mentally time-travel"--remember past events in detail without attending to all intervening events.

In popular media, there is often a connection drawn between the advent of awareness in artificial agents and those same agents simultaneously achieving human or superhuman level intelligence. In this work, we explore the validity and potential application of this seemingly intuitive link between consciousness and intelligence. We do so by examining the cognitive abilities associated with three contemporary theories of conscious function: Global Workspace Theory (GWT), Information Generation Theory (IGT), and Attention Schema Theory (AST). We find that all three theories specifically relate conscious function to some aspect of domain-general intelligence in humans. With this insight, we turn to the field of Artificial Intelligence (AI) and find that, while still far from demonstrating general intelligence, many state-of-the-art deep learning methods have begun to incorporate key aspects of each of the three functional theories. Having identified this trend, we use the motivating example of mental time travel in humans to propose ways in which insights from each of the three theories may be combined into a single unified and implementable model. Given that it is made possible by cognitive abilities underlying each of the three functional theories, artificial agents capable of mental time travel would not only possess greater general intelligence than current approaches, but also be more consistent with our current understanding of the functional role of consciousness in humans, thus making it a promising near-term goal for AI research.

Neural pathways in the brain's hippocampus, a complex structure embedded deep into temporal lobe, enables humans to time travel through life memories, a new study reveals. A team of neuroscientists, Led by researchers at the Brain and Cognition Research Center (CerCo) at the French National Centre for Scientific Research, found these neurons, or time cells, fire during specific moments and may contribute to memory by encoding information about the time and order of events. While monitoring brain activity in an experiment, researchers said they were able to decode different moments in time based on the activity of the entire group of neurons. Along with finding this complex process in the brain, the results bring hope to those with conditions that affect memory and the ability to process time, including Alzheimer's and Dementia, as scientists could soon find a way to treat the neural pathway. Leila Reddy, a neuroscientist who led the research, told VICE: 'The hippocampus is important for judging the temporal order of events (among other things), and damage to the hippocampus can result in an impairment of memory for temporal order (for example remembering the order of a list of items).

Human "exceptionalism" is for many people an unquestioned assumption. For the religious, it is a God-given fact; for humanists, it is a celebration of our unique mental capacities.

Ravens are known for being remarkably intelligent. Now a new study has revealed that these clever birds plan for the future, just like us. They can imagine future events via'mental time travel' and are capable of exercising self-control to delay gratification, researchers found. This skill of future planning was thought to be exclusive to humans and great apes. As ravens and great apes have not shared a common ancestor for more than 300 million years, these results suggest'planning' abilities evolved independently of one another.