Related papers: Episodic memory governs choices: An RNN-based rein…
Cognitive Psychology and related disciplines have identified several critical mechanisms that enable intelligent biological agents to learn to solve complex problems. There exists pressing evidence that the cognitive mechanisms that enable…
Drawing an inspiration from behavioral studies of human decision making, we propose here a more general and flexible parametric framework for reinforcement learning that extends standard Q-learning to a two-stream model for processing…
Working memory is a central cognitive ability crucial for intelligent decision-making. Recent experimental and computational work studying working memory has primarily used categorical (i.e., one-hot) inputs, rather than ecologically…
Expectation for the emergence of higher functions is getting larger in the framework of end-to-end reinforcement learning using a recurrent neural network. However, the emergence of "thinking" that is a typical higher function is difficult…
Most current AI models have little ability to store and later retrieve a record or representation of what they do. In human cognition, episodic memories play an important role in both recall of the past as well as planning for the future.…
The hippocampus and the striatum support episodic and procedural memory, respectively, and "place" and "response" learning within spatial navigation. Recently this dichotomy has been linked to "model-based" and "model-free" reinforcement…
The brain is a nonlinear and highly Recurrent Neural Network (RNN). This RNN is surprisingly plastic and supports our astonishing ability to learn and execute complex tasks. However, learning is incredibly complicated due to the brain's…
The spiking activity of principal cells in mammalian hippocampus encodes an internalized neuronal representation of the ambient space---a cognitive map. Once learned, such a map enables the animal to navigate a given environment for a long…
We introduce a novel training procedure for policy gradient methods wherein episodic memory is used to optimize the hyperparameters of reinforcement learning algorithms on-the-fly. Unlike other hyperparameter searches, we formulate…
Recent successes combine reinforcement learning algorithms and deep neural networks, despite reinforcement learning not being widely applied to robotics and real world scenarios. This can be attributed to the fact that current…
How the human vision system addresses the object identity-preserving recognition problem is largely unknown. Here, we use a vision recognition-reconstruction network (RRN) to investigate the development, recognition, learning and forgetting…
We study reinforcement learning (RL) problems in which agents observe the reward or transition realizations at their current state before deciding which action to take. Such observations are available in many applications, including…
Memory models such as Recurrent Neural Networks (RNNs) and Transformers address Partially Observable Markov Decision Processes (POMDPs) by mapping trajectories to latent Markov states. Neither model scales particularly well to long…
Memory-Augmented Neural Networks (MANNs) are a class of neural networks equipped with an external memory, and are reported to be effective for tasks requiring a large long-term memory and its selective use. The core module of a MANN is…
As Large Language Models (LLMs) evolve from text-completion tools into fully fledged agents operating in dynamic environments, they must address the challenge of continually learning and retaining long-term knowledge. Many biological…
In continual learning (CL), an agent learns from a stream of tasks leveraging prior experience to transfer knowledge to future tasks. It is an ideal framework to decrease the amount of supervision in the existing learning algorithms. But…
How do people decide how long to continue in a task, when to switch, and to which other task? Understanding the mechanisms that underpin task interleaving is a long-standing goal in the cognitive sciences. Prior work suggests greedy…
Although reinforcement learning has seen tremendous success recently, this kind of trial-and-error learning can be impractical or inefficient in complex environments. The use of demonstrations, on the other hand, enables agents to benefit…
Understanding pedestrian behavior is crucial for the safe deployment of Autonomous Vehicles (AVs) in urban environments. Traditional pedestrian behavior models often fall into two categories: mechanistic models, which do not generalize well…
Reinforcement learning (RL) can be formulated as a sequence modeling problem, where models predict future actions based on historical state-action-reward sequences. Current approaches typically require long trajectory sequences to model the…