Measuring Learning Progress via Gradient-Momentum Coupling

Measuring learning progress is essential for curiosity-driven exploration in reinforcement learning, but widely used signals such as prediction error often fail to distinguish meaningful, learnable patterns from random noise. This paper proposes Gradient-Momentum Coupling (GMC), a signal derived from optimization dynamics that quantifies how useful each sample's gradient is for ongoing learning by measuring its per-parameter normalized absolute product with the momentum from previous gradients. By leveraging momentum's natural filtering of noise and oscillations, GMC identifies samples that contribute to ongoing parameter updates. Controlled experiments demonstrate noise robustness and emergent curriculum learning, with the signal prioritizing tasks by learning speed rather than difficulty. Experiments on MiniGrid suggest that replacing prediction error with GMC within existing curiosity-driven architectures can improve robustness to observation noise.

Evolutionary Discovery of Reinforcement Learning Algorithms via Large Language Models

Reinforcement learning algorithms are defined by their learning update rules, which are typically hand-designed and fixed. We present an evolutionary framework for discovering reinforcement learning algorithms by searching directly over executable update rules that implement complete training procedures. The approach builds on REvolve, an evolutionary system that uses large language models as generative variation operators, and extends it from reward-function discovery to algorithm discovery. To promote the emergence of nonstandard learning rules, the search excludes canonical mechanisms such as actor--critic structures, temporal-difference losses, and value bootstrapping. Because reinforcement learning algorithms are highly sensitive to internal scalar parameters, we introduce a post-evolution refinement stage in which a large language model proposes feasible hyperparameter ranges for each evolved update rule. Evaluated end-to-end by full training runs on multiple Gymnasium benchmarks, the discovered algorithms achieve competitive performance relative to established baselines, including SAC, PPO, DQN, and A2C.

COvolve: Adversarial Co-Evolution of Large-Language-Model-Generated Policies and Environments via Two-Player Zero-Sum Game

A central challenge in building continually improving agents is that training environments are typically static or manually constructed. This restricts continual learning and generalization beyond the training distribution. We address this with COvolve, a co-evolutionary framework that leverages large language models (LLMs) to generate both environments and agent policies, expressed as executable Python code. We model the interaction between environment and policy designers as a two-player zero-sum game, ensuring adversarial co-evolution in which environments expose policy weaknesses and policies adapt in response. This process induces an automated curriculum in which environments and policies co-evolve toward increasing complexity. To guarantee robustness and prevent forgetting as the curriculum progresses, we compute the mixed-strategy Nash equilibrium (MSNE) of the zero-sum game, thereby yielding a meta-policy. This MSNE meta-policy ensures that the agent does not forget to solve previously seen environments while learning to solve previously unseen ones. Experiments in urban driving, symbolic maze-solving, and geometric navigation showcase that COvolve produces progressively more complex environments. Our results demonstrate the potential of LLM-driven co-evolution to achieve open-ended learning without predefined task distributions or manual intervention.

LAP: A Language-Aware Planning Model For Procedure Planning In Instructional Videos

Procedure planning requires a model to predict a sequence of actions that transform a start visual observation into a goal in instructional videos. While most existing methods rely primarily on visual observations as input, they often struggle with the inherent ambiguity where different actions can appear visually similar. In this work, we argue that language descriptions offer a more distinctive representation in the latent space for procedure planning. We introduce Language-Aware Planning (LAP), a novel method that leverages the expressiveness of language to bridge visual observation and planning. LAP uses a finetuned Vision Language Model (VLM) to translate visual observations into text descriptions and to predict actions and extract text embeddings. These text embeddings are more distinctive than visual embeddings and are used in a diffusion model for planning action sequences. We evaluate LAP on three procedure planning benchmarks: CrossTask, Coin, and NIV. LAP achieves new state-of-the-art performance across multiple metrics and time horizons by large margin, demonstrating the significant advantage of language-aware planning.

Towards a Comprehensive Theory of Reservoir Computing

In reservoir computing, an input sequence is processed by a recurrent neural network, the reservoir, which transforms it into a spatial pattern that a shallow readout network can then exploit for tasks such as memorization and time-series prediction or classification. Echo state networks (ESN) are a model class in which the reservoir is a traditional artificial neural network. This class contains many model types, each with sets of hyperparameters. Selecting models and parameter settings for particular applications requires a theory for predicting and comparing performances. Here, we demonstrate that recent developments of perceptron theory can be used to predict the memory capacity and accuracy of a wide variety of ESN models, including reservoirs with linear neurons, sigmoid nonlinear neurons, different types of recurrent matrices, and different types of readout networks. Across thirty variants of ESNs, we show that empirical results consistently confirm the theory's predictions. As a practical demonstration, the theory is used to optimize memory capacity of an ESN in the entire joint parameter space. Further, guided by the theory, we propose a novel ESN model with a readout network that does not require training, and which outperforms earlier ESN models without training. Finally, we characterize the geometry of the readout networks in ESNs, which reveals that many ESN models exhibit a similar regular simplex geometry as has been observed in the output weights of deep neural networks.

Efficient Hyperdimensional Computing with Modular Composite Representations

The modular composite representation (MCR) is a computing model that represents information with high-dimensional integer vectors using modular arithmetic. Originally proposed as a generalization of the binary spatter code model, it aims to provide higher representational power while remaining a lighter alternative to models requiring high-precision components. Despite this potential, MCR has received limited attention. Systematic analyses of its trade-offs and comparisons with other models are lacking, sustaining the perception that its added complexity outweighs the improved expressivity. In this work, we revisit MCR by presenting its first extensive evaluation, demonstrating that it achieves a unique balance of capacity, accuracy, and hardware efficiency. Experiments measuring capacity demonstrate that MCR outperforms binary and integer vectors while approaching complex-valued representations at a fraction of their memory footprint. Evaluation on 123 datasets confirms consistent accuracy gains and shows that MCR can match the performance of binary spatter codes using up to 4x less memory. We investigate the hardware realization of MCR by showing that it maps naturally to digital logic and by designing the first dedicated accelerator. Evaluations on basic operations and 7 selected datasets demonstrate a speedup of up to 3 orders of magnitude and significant energy reductions compared to software implementation. When matched for accuracy against binary spatter codes, MCR achieves on average 3.08x faster execution and 2.68x lower energy consumption. These findings demonstrate that, although MCR requires more sophisticated operations than binary spatter codes, its modular arithmetic and higher per-component precision enable lower dimensionality. When realized with dedicated hardware, this results in a faster, more energy-efficient, and high-precision alternative to existing models.

Relative Navigation and Dynamic Target Tracking for Autonomous Underwater Proximity Operations

Estimating a target's 6-DoF motion in underwater proximity operations is difficult because the chaser lacks target-side proprioception and the available relative observations are sparse, noisy, and often partial (e.g., Ultra-Short Baseline (USBL) positions). Without a motion prior, factor-graph maximum a posteriori estimation is underconstrained: consecutive target states are weakly linked and orientation can drift. We propose a generalized constant-twist motion prior defined on the tangent space of Lie groups that enforces temporally consistent trajectories across all degrees of freedom; in SE(3) it couples translation and rotation in the body frame. We present a ternary factor and derive its closed-form Jacobians based on standard Lie group operations, enabling drop-in use for trajectories on arbitrary Lie groups. We evaluate two deployment modes: (A) an SE(3)-only representation that regularizes orientation even when only position is measured, and (B) a mode with boundary factors that switches the target representation between SE(3) and 3D position while applying the same generalized constant-twist prior across representation changes. Validation on a real-world dynamic docking scenario dataset shows consistent ego-target trajectory estimation through USBL-only and optical relative measurement segments with an improved relative tracking accuracy compared to the noisy measurements to the target. Because the construction relies on standard Lie group primitives, it is portable across state manifolds and sensing modalities.

Interactive Double Deep Q-network: Integrating Human Interventions and Evaluative Predictions in Reinforcement Learning of Autonomous Driving

Integrating human expertise with machine learning is crucial for applications demanding high accuracy and safety, such as autonomous driving. This study introduces Interactive Double Deep Q-network (iDDQN), a Human-in-the-Loop (HITL) approach that enhances Reinforcement Learning (RL) by merging human insights directly into the RL training process, improving model performance. Our proposed iDDQN method modifies the Q-value update equation to integrate human and agent actions, establishing a collaborative approach for policy development. Additionally, we present an offline evaluative framework that simulates the agent's trajectory as if no human intervention had occurred, to assess the effectiveness of human interventions. Empirical results in simulated autonomous driving scenarios demonstrate that iDDQN outperforms established approaches, including Behavioral Cloning (BC), HG-DAgger, Deep Q-Learning from Demonstrations (DQfD), and vanilla DRL in leveraging human expertise for improving performance and adaptability.

Evaluation of Coordination Strategies for Underground Automated Vehicle Fleets in Mixed Traffic

This study investigates the efficiency and safety outcomes of implementing different adaptive coordination models for automated vehicle (AV) fleets, managed by a centralized coordinator that dynamically responds to human-controlled vehicle behavior. The simulated scenarios replicate an underground mining environment characterized by narrow tunnels with limited connectivity. To address the unique challenges of such settings, we propose a novel metric - Path Overlap Density (POD) - to predict efficiency and potentially the safety performance of AV fleets. The study also explores the impact of map features on AV fleets performance. The results demonstrate that both AV fleet coordination strategies and underground tunnel network characteristics significantly influence overall system performance. While map features are critical for optimizing efficiency, adaptive coordination strategies are essential for ensuring safe operations.

REvolve: Reward Evolution with Large Language Models for Autonomous Driving

Designing effective reward functions is crucial to training reinforcement learning (RL) algorithms. However, this design is non-trivial, even for domain experts, due to the subjective nature of certain tasks that are hard to quantify explicitly. In recent works, large language models (LLMs) have been used for reward generation from natural language task descriptions, leveraging their extensive instruction tuning and commonsense understanding of human behavior. In this work, we hypothesize that LLMs, guided by human feedback, can be used to formulate human-aligned reward functions. Specifically, we study this in the challenging setting of autonomous driving (AD), wherein notions of "good" driving are tacit and hard to quantify. To this end, we introduce REvolve, an evolutionary framework that uses LLMs for reward design in AD. REvolve creates and refines reward functions by utilizing human feedback to guide the evolution process, effectively translating implicit human knowledge into explicit reward functions for training (deep) RL agents. We demonstrate that agents trained on REvolve-designed rewards align closely with human driving standards, thereby outperforming other state-of-the-art baselines.