Related papers: Decision-making with Speculative Opponent Models

We introduce D2AC, a new model-free reinforcement learning (RL) algorithm designed to train expressive diffusion policies online effectively. At its core is a policy improvement objective that avoids the high variance of typical policy…

We study the problem of off-policy critic evaluation in several variants of value-based off-policy actor-critic algorithms. Off-policy actor-critic algorithms require an off-policy critic evaluation step, to estimate the value of the new…

Information is often stored in a distributed and proprietary form, and agents who own information are often self-interested and require incentives to reveal their information. Suitable mechanisms are required to elicit and aggregate such…

Multi-agent systems often require agents to collaborate with or compete against other agents with diverse goals, behaviors, or strategies. Agent modeling is essential when designing adaptive policies for intelligent machine agents in…

In cooperative multiagent planning, it can often be beneficial for an agent to make commitments about aspects of its behavior to others, allowing them in turn to plan their own behaviors without taking the agent's detailed behavior into…

In distributed predictive control structures, communication among agents is required to achieve a consensus and approach an optimal global behavior. Such negotiation mechanisms are sensitive to attacks on these exchanges. This paper…

Reinforcement learning (RL) has achieved remarkable performance in numerous sequential decision making and control tasks. However, a common problem is that learned nearly optimal policy always overfits to the training environment and may…

Deterministic-policy actor-critic algorithms for continuous control improve the actor by plugging its actions into the critic and ascending the action-value gradient, which is obtained by chaining the actor's Jacobian matrix with the…

Reinforcement learning with multiple, potentially conflicting objectives is pervasive in real-world applications, while this problem remains theoretically under-explored. This paper tackles the multi-objective reinforcement learning (MORL)…

This paper presents a trust-based predictive multi-agent consensus protocol that analyses neighbours' anticipation data and makes coordination decisions. Agents in the network share their future predicted data over a finite look-ahead…

Complex behaviors are often driven by an internal model, which integrates sensory information over time and facilitates long-term planning. Inferring an agent's internal model is a crucial ingredient in social interactions (theory of mind),…

We present an online multi-task learning approach for adaptive nonlinear control, which we call Online Meta-Adaptive Control (OMAC). The goal is to control a nonlinear system subject to adversarial disturbance and unknown…

Current model-based reinforcement learning approaches use the model simply as a learned black-box simulator to augment the data for policy optimization or value function learning. In this paper, we show how to make more effective use of the…

Distributed estimation that recruits potentially large groups of humans to collect data about a phenomenon of interest has emerged as a paradigm applicable to a broad range of detection and estimation tasks. However, it also presents a…

In safety-critical domains where online data collection is infeasible, offline reinforcement learning (RL) offers an attractive alternative but only if policies deliver high returns without incurring catastrophic lower-tail risk. Prior work…

Blame attribution is one of the key aspects of accountable decision making, as it provides means to quantify the responsibility of an agent for a decision making outcome. In this paper, we study blame attribution in the context of…

Extracting relevant information from a stream of high-dimensional observations is a central challenge for deep reinforcement learning agents. Actor-critic algorithms add further complexity to this challenge, as it is often unclear whether…

This paper proposes the Cooperative Soft Actor Critic (CSAC) method of enabling consecutive reinforcement learning agents to cooperatively solve a long time horizon multi-stage task. This method is achieved by modifying the policy of each…

A variety of theoretically-sound policy gradient algorithms exist for the on-policy setting due to the policy gradient theorem, which provides a simplified form for the gradient. The off-policy setting, however, has been less clear due to…

Medical decision-making often involves integrating knowledge from multiple clinical specialties, typically achieved through multidisciplinary teams. Inspired by this collaborative process, recent work has leveraged large language models…