Search Results for author:
Found 44 papers, 11 papers with code
Policy Space Response Oracles: A Survey
In game theory, a game refers to a model of interaction among rational decision-makers or players, making choices with the goal of achieving their individual objectives.
When Do Off-Policy and On-Policy Policy Gradient Methods Align?
A well-established off-policy objective is the excursion objective.
What Lies beyond the Pareto Front? A Survey on Decision-Support Methods for Multi-Objective Optimization
We present a review that unifies decision-support methods for exploring the solutions produced by multi-objective optimization (MOO) algorithms.
Bad Habits: Policy Confounding and Out-of-Trajectory Generalization in RL
In this paper, we provide a mathematical characterization of this phenomenon, which we refer to as policy confounding, and show, through a series of examples, when and how it occurs in practice.
What model does MuZero learn?
Model-based reinforcement learning has drawn considerable interest in recent years, given its promise to improve sample efficiency.
Towards a Unifying Model of Rationality in Multiagent Systems
Multiagent systems deployed in the real world need to cooperate with other agents (including humans) nearly as effectively as these agents cooperate with one another.
Safe Multi-agent Learning via Trapping Regions
One of the main challenges of multi-agent learning lies in establishing convergence of the algorithms, as, in general, a collection of individual, self-serving agents is not guaranteed to converge with their joint policy, when learning concurrently.
Uncoupled Learning of Differential Stackelberg Equilibria with Commitments
A natural solution concept for many multiagent settings is the Stackelberg equilibrium, under which a ``leader'' agent selects a strategy that maximizes its own payoff assuming the ``follower'' chooses their best response to this strategy.
An Analysis of Model-Based Reinforcement Learning From Abstracted Observations
This result makes it possible to extend the guarantees of existing MBRL algorithms to the setting with abstraction.
Model-based Reinforcement Learning
reinforcement-learning
+1
Distributed Influence-Augmented Local Simulators for Parallel MARL in Large Networked Systems
Due to its high sample complexity, simulation is, as of today, critical for the successful application of reinforcement learning.
On the Impossibility of Learning to Cooperate with Adaptive Partner Strategies in Repeated Games
Learning to cooperate with other agents is challenging when those agents also possess the ability to adapt to our own behavior.
Best-Response Bayesian Reinforcement Learning with Bayes-adaptive POMDPs for Centaurs
Centaurs are half-human, half-AI decision-makers where the AI's goal is to complement the human.
BADDr: Bayes-Adaptive Deep Dropout RL for POMDPs
Under this parameterization, in contrast to previous work, the belief over the state and dynamics is a more scalable inference problem.
Influence-Augmented Local Simulators: A Scalable Solution for Fast Deep RL in Large Networked Systems
Learning effective policies for real-world problems is still an open challenge for the field of reinforcement learning (RL).
Online Planning in POMDPs with Self-Improving Simulators
To plan reliably and efficiently while the approximate simulator is learning, we develop a method that adaptively decides which simulator to use for every simulation, based on a statistic that measures the accuracy of the approximate simulator.
MORAL: Aligning AI with Human Norms through Multi-Objective Reinforced Active Learning
Inferring reward functions from demonstrations and pairwise preferences are auspicious approaches for aligning Reinforcement Learning (RL) agents with human intentions.
Multi-Agent MDP Homomorphic Networks
This paper introduces Multi-Agent MDP Homomorphic Networks, a class of networks that allows distributed execution using only local information, yet is able to share experience between global symmetries in the joint state-action space of cooperative multi-agent systems.
Difference Rewards Policy Gradients
Policy gradient methods have become one of the most popular classes of algorithms for multi-agent reinforcement learning.
Analog Circuit Design with Dyna-Style Reinforcement Learning
One of the aspects that makes this problem challenging to optimize, is that measuring the performance of candidate configurations with simulation can be computationally expensive, particularly in the post-layout design.
Loss Bounds for Approximate Influence-Based Abstraction
Sequential decision making techniques hold great promise to improve the performance of many real-world systems, but computational complexity hampers their principled application.
Multi-agent active perception with prediction rewards
The accuracy is quantified by a centralized prediction reward determined by a centralized decision-maker who perceives the observations gathered by all agents after the task ends.
Influence-Augmented Online Planning for Complex Environments
In this work, we propose influence-augmented online planning, a principled method to transform a factored simulator of the entire environment into a local simulator that samples only the state variables that are most relevant to the observation and reward of the planning agent and captures the incoming influence from the rest of the environment using machine learning methods.
Exploiting Submodular Value Functions For Scaling Up Active Perception
Furthermore, we show that, under certain conditions, including submodularity, the value function computed using greedy PBVI is guaranteed to have bounded error with respect to the optimal value function.
Real-Time Resource Allocation for Tracking Systems
Automated tracking is key to many computer vision applications.
MDP Homomorphic Networks: Group Symmetries in Reinforcement Learning
MDP homomorphic networks are neural networks that are equivariant under symmetries in the joint state-action space of an MDP.
Sensor Data for Human Activity Recognition: Feature Representation and Benchmarking
In HAR, the development of Activity Recognition models is dependent upon the data captured by these devices and the methods used to analyse them, which directly affect performance metrics.
Diversity in Action: General-Sum Multi-Agent Continuous Inverse Optimal Control
Traffic scenarios are inherently interactive.
Mimicking Evolution with Reinforcement Learning
This work proposes Evolution via Evolutionary Reward (EvER) that allows learning to single-handedly drive the search for policies with increasingly evolutionary fitness by ensuring the alignment of the reward function with the fitness function.
Decentralized MCTS via Learned Teammate Models
Decentralized online planning can be an attractive paradigm for cooperative multi-agent systems, due to improved scalability and robustness.
Plannable Approximations to MDP Homomorphisms: Equivariance under Actions
We introduce a contrastive loss function that enforces action equivariance on the learned representations.
Influence-aware Memory Architectures for Deep Reinforcement Learning
Due to its perceptual limitations, an agent may have too little information about the state of the environment to act optimally.
A Sufficient Statistic for Influence in Structured Multiagent Environments
In these ways, this paper deepens our understanding of abstraction in a wide range of sequential decision making settings, providing the basis for new approaches and algorithms for a large class of problems.
Learning from Demonstration in the Wild
Learning from demonstration (LfD) is useful in settings where hand-coding behaviour or a reward function is impractical.
Beyond Local Nash Equilibria for Adversarial Networks
Save for some special cases, current training methods for Generative Adversarial Networks (GANs) are at best guaranteed to converge to a `local Nash equilibrium` (LNE).
Learning in POMDPs with Monte Carlo Tree Search
The POMDP is a powerful framework for reasoning under outcome and information uncertainty, but constructing an accurate POMDP model is difficult.
GANGs: Generative Adversarial Network Games
We introduce Generative Adversarial Network Games (GANGs), which explicitly model a finite zero-sum game between a generator ($G$) and classifier ($C$) that use mixed strategies.
Structure in the Value Function of Two-Player Zero-Sum Games of Incomplete Information
Zero-sum stochastic games provide a rich model for competitive decision making.
Probably Approximately Correct Greedy Maximization with Efficient Bounds on Information Gain for Sensor Selection
Submodular function maximization finds application in a variety of real-world decision-making problems.
Scaling POMDPs For Selecting Sellers in E-markets-Extended Version
In multiagent e-marketplaces, buying agents need to select good sellers by querying other buyers (called advisors).
Solving Transition-Independent Multi-agent MDPs with Sparse Interactions (Extended version)
In cooperative multi-agent sequential decision making under uncertainty, agents must coordinate to find an optimal joint policy that maximises joint value.
Exploiting Anonymity in Approximate Linear Programming: Scaling to Large Multiagent MDPs (Extended Version)
We present an approach to mitigate this limitation for certain types of multiagent systems, exploiting a property that can be thought of as "anonymous influence" in the factored MDP.
Influence-Optimistic Local Values for Multiagent Planning --- Extended Version
Recent years have seen the development of methods for multiagent planning under uncertainty that scale to tens or even hundreds of agents.
Scalable Planning and Learning for Multiagent POMDPs: Extended Version
Online, sample-based planning algorithms for POMDPs have shown great promise in scaling to problems with large state spaces, but they become intractable for large action and observation spaces.
Exploiting Agent and Type Independence in Collaborative Graphical Bayesian Games
Such problems can be modeled as collaborative Bayesian games in which each agent receives private information in the form of its type.
