Related papers: Structural Credit Assignment with Coordinated Expl…

The brain must robustly store a large number of memories, corresponding to the many events encountered over a lifetime. However, the number of memory states in existing neural network models either grows weakly with network size or recall…

Inspired by the natural nervous system, synaptic plasticity rules are applied to train spiking neural networks with local information, making them suitable for online learning on neuromorphic hardware. However, when such rules are…

Deep artificial neural networks have surpassed human-level performance across a diverse array of complex learning tasks, establishing themselves as indispensable tools in both social applications and scientific research. Despite these…

Many continuous control tasks have easily formulated objectives, yet using them directly as a reward in reinforcement learning (RL) leads to suboptimal policies. Therefore, many classical control tasks guide RL training using complex…

Command line interface (CLI) agents are emerging as a practical paradigm for agent-computer interaction over evolving filesystems, executable command line programs, and online execution feedback. Recent work has used reinforcement learning…

Offline reinforcement learning refers to the process of learning policies from fixed datasets, without requiring additional environment interaction. However, it often relies on well-defined reward functions, which are difficult and…

How to best explore in domains with sparse, delayed, and deceptive rewards is an important open problem for reinforcement learning (RL). This paper considers one such domain, the recently-proposed multi-agent benchmark of Pommerman. This…

Self-evaluation, a model's ability to assess the correctness of its own output, is crucial for Large Multimodal Models (LMMs) to achieve self-improvement in multi-turn conversations, yet largely absent in foundation models. Recent work has…

Training Artificial Neural Networks poses a challenging and critical problem in machine learning. Despite the effectiveness of gradient-based learning methods, such as Stochastic Gradient Descent (SGD), in training neural networks, they do…

Reinforcement Learning with Rubric Rewards (RLRR) is a framework that extends conventional reinforcement learning from human feedback (RLHF) and verifiable rewards (RLVR) by replacing scalar preference signals with structured,…

The neural plausibility of backpropagation has long been disputed, primarily for its use of non-local weight transport $-$ the biologically dubious requirement that one neuron instantaneously measure the synaptic weights of another. Until…

Neuromorphic architectures, which incorporate parallel and in-memory processing, are crucial for accelerating artificial neural network (ANN) computations. This work presents a novel memristor-based multi-layer neural network (memristive…

A computational problem in biological reward-based learning is how credit assignment is performed in the nucleus accumbens (NAc). Much research suggests that NAc dopamine encodes temporal-difference (TD) errors for learning value…

In the field of image recognition, spiking neural networks (SNNs) have achieved performance comparable to conventional artificial neural networks (ANNs). In such applications, SNNs essentially function as traditional neural networks with…

Understanding how learning algorithms shape the computational strategies that emerge in neural networks remains a fundamental challenge in machine intelligence. While network architectures receive extensive attention, the role of the…

Network architectures and learning principles are key in forming complex functions in artificial neural networks (ANNs) and spiking neural networks (SNNs). SNNs are considered the new-generation artificial networks by incorporating more…

Learning a policy capable of moving an agent between any two states in the environment is important for many robotics problems involving navigation and manipulation. Due to the sparsity of rewards in such tasks, applying reinforcement…

Autonomous 3D environment exploration is a fundamental task for various applications such as navigation. The goal of exploration is to investigate a new environment and build its occupancy map efficiently. In this paper, we propose a new…

A new approach for efficiently exploring the configuration space and computing the free energy of large atomic and molecular systems is proposed, motivated by an analogy with reinforcement learning. There are two major components in this…

Exploration efficiency is a challenging problem in multi-agent reinforcement learning (MARL), as the policy learned by confederate MARL depends on the collaborative approach among multiple agents. Another important problem is the less…