Related papers: Approximating Gradients for Differentiable Quality…
Quality-diversity (QD) algorithms search for a set of good solutions which cover a space as defined by behavior metrics. This simultaneous focus on quality and diversity with explicit metrics sets QD algorithms apart from standard single-…
We present a novel definition of the reinforcement learning state, actions and reward function that allows a deep Q-network (DQN) to learn to control an optimization hyperparameter. Using Q-learning with experience replay, we train two DQNs…
We consider the problem of scheduling in constrained queueing networks with a view to minimizing packet delay. Modern communication systems are becoming increasingly complex, and are required to handle multiple types of traffic with widely…
Quality Diversity (QD) algorithms have been proposed to search for a large collection of both diverse and high-performing solutions instead of a single set of local optima. While early QD algorithms view the objective and descriptor…
This paper deals with distributed policy optimization in reinforcement learning, which involves a central controller and a group of learners. In particular, two typical settings encountered in several applications are considered:…
Reinforcement learning (RL) is one of the most practical ways to learn from real-life use-cases. Motivated from the cognitive methods used by humans makes it a widely acceptable strategy in the field of artificial intelligence. Most of the…
Agent skills provide a lightweight way to adapt LLM agents to specialized domains by storing reusable procedural knowledge in structured files. However, whether downloaded from third parties or self-generated, these skills are often…
Our work focuses on training RL agents on multiple visually diverse environments to improve observational generalization performance. In prior methods, policy and value networks are separately optimized using a disjoint network architecture…
This paper develops the first policy gradient method with global optimality guarantee and complexity analysis for robust reinforcement learning under model mismatch. Robust reinforcement learning is to learn a policy robust to model…
Understanding how humans collaborate and communicate in teams is essential for improving human-agent teaming and AI-assisted decision-making. However, relying solely on data from large-scale user studies is impractical due to logistical,…
We propose a novel approach to address one aspect of the non-stationarity problem in multi-agent reinforcement learning (RL), where the other agents may alter their policies due to environment changes during execution. This violates the…
Deep reinforcement learning is a technique for solving problems in a variety of environments, ranging from Atari video games to stock trading. This method leverages deep neural network models to make decisions based on observations of a…
Among the great successes of Reinforcement Learning (RL), self-play algorithms play an essential role in solving competitive games. Current self-play algorithms optimize the agent to maximize expected win-rates against its current or…
In this work, we provide an extended discussion of a new approach to explainable Reinforcement Learning called Diverse Near-Optimal Alternatives (DNA), first proposed at L4DC 2025. DNA seeks a set of reasonable "options" for…
Deep reinforcement learning (RL) has achieved several high profile successes in difficult decision-making problems. However, these algorithms typically require a huge amount of data before they reach reasonable performance. In fact, their…
Classical reinforcement learning (RL) aims to optimize the expected cumulative reward. In this work, we consider the RL setting where the goal is to optimize the quantile of the cumulative reward. We parameterize the policy controlling…
Policy gradient methods are often applied to reinforcement learning in continuous multiagent games. These methods perform local search in the joint-action space, and as we show, they are susceptable to a game-theoretic pathology known as…
Reinforcement learning studies how an agent should interact with an environment to maximize its cumulative reward. A standard way to study this question abstractly is to ask how many samples an agent needs from the environment to learn an…
Learning algorithms, like Quality-Diversity (QD), can be used to acquire repertoires of diverse robotics skills. This learning is commonly done via computer simulation due to the large number of evaluations required. However, training in a…
Policy gradient methods have shown success in learning control policies for high-dimensional dynamical systems. Their biggest downside is the amount of exploration they require before yielding high-performing policies. In a lifelong…