Search Results for author:
Found 35 papers, 15 papers with code
The Wasserstein Believer: Learning Belief Updates for Partially Observable Environments through Reliable Latent Space Models
Keeping a probability distribution that models the belief over what the true state is can be used as a sufficient statistic of the history, but its computation requires access to the model of the environment and is also intractable.
Evaluating COVID-19 vaccine allocation policies using Bayesian $m$-top exploration
$m$-top exploration allows the algorithm to learn $m$ policies for which it expects the highest utility, enabling experts to inspect this small set of alternative strategies, along with their quantified uncertainty.
Transferring Multiple Policies to Hotstart Reinforcement Learning in an Air Compressor Management Problem
Many instances of similar or almost-identical industrial machines or tools are often deployed at once, or in quick succession.
Sample-Efficient Multi-Objective Learning via Generalized Policy Improvement Prioritization
Finally, we introduce a bound that characterizes the maximum utility loss (with respect to the optimal solution) incurred by the partial solutions computed by our method throughout learning.
MO-Gym: A Library of Multi-Objective Reinforcement Learning Environments
We introduce MO-Gym, an extensible library containing a diverse set of multi-objective reinforcement learning environments.
Safe reinforcement learning for multi-energy management systems with known constraint functions
Reinforcement learning (RL) is a promising optimal control technique for multi-energy management systems.
Exploring the Pareto front of multi-objective COVID-19 mitigation policies using reinforcement learning
As decision making in the context of epidemic mitigation is hard, reinforcement learning provides a methodology to automatically learn prevention strategies in combination with complex epidemic models.
Pareto Conditioned Networks
In multi-objective optimization, learning all the policies that reach Pareto-efficient solutions is an expensive process.
Local Advantage Networks for Cooperative Multi-Agent Reinforcement Learning
Moreover, when the number of agents becomes large, LAN uses significantly fewer parameters than QPLEX or even QMIX.
Distillation of RL Policies with Formal Guarantees via Variational Abstraction of Markov Decision Processes (Technical Report)
Finally, we show how one can use a policy obtained via state-of-the-art RL to efficiently train a variational autoencoder that yields a discrete latent model with provably approximately correct bisimulation guarantees.
Preference Communication in Multi-Objective Normal-Form Games
We consider preference communication in two-player multi-objective normal-form games.
Dealing with Expert Bias in Collective Decision-Making
Quite some real-world problems can be formulated as decision-making problems wherein one must repeatedly make an appropriate choice from a set of alternatives.
Synthesising Reinforcement Learning Policies through Set-Valued Inductive Rule Learning
Then, to ensure that the rules explain a valid, non-degenerate policy, we introduce a refinement algorithm that fine-tunes the rules to obtain good performance when executed in the environment.
Model-predictive control and reinforcement learning in multi-energy system case studies
Model-predictive-control (MPC) offers an optimal control technique to establish and ensure that the total operation cost of multi-energy systems remains at a minimum while fulfilling all system constraints.
A Practical Guide to Multi-Objective Reinforcement Learning and Planning
Real-world decision-making tasks are generally complex, requiring trade-offs between multiple, often conflicting, objectives.
Opponent Learning Awareness and Modelling in Multi-Objective Normal Form Games
We contribute novel actor-critic and policy gradient formulations to allow reinforcement learning of mixed strategies in this setting, along with extensions that incorporate opponent policy reconstruction and learning with opponent learning awareness (i. e., learning while considering the impact of one's policy when anticipating the opponent's learning step).
Deep reinforcement learning for large-scale epidemic control
For this reason, we investigate a deep reinforcement learning approach to automatically learn prevention strategies in the context of pandemic influenza.
A utility-based analysis of equilibria in multi-objective normal form games
In multi-objective multi-agent systems (MOMAS), agents explicitly consider the possible tradeoffs between conflicting objective functions.
Model-based Multi-Agent Reinforcement Learning with Cooperative Prioritized Sweeping
We present a new model-based reinforcement learning algorithm, Cooperative Prioritized Sweeping, for efficient learning in multi-agent Markov decision processes.
Model-based Reinforcement Learning
Multi-agent Reinforcement Learning
+3
Fleet Control using Coregionalized Gaussian Process Policy Iteration
In many settings, as for example wind farms, multiple machines are instantiated to perform the same task, which is called a fleet.
Multi-Agent Thompson Sampling for Bandit Applications with Sparse Neighbourhood Structures
In this task, wind turbines must coordinate their alignments with respect to the incoming wind vector in order to optimize power production.
IPC-Net: 3D point-cloud segmentation using deep inter-point convolutional layers
In general, our approach outperforms PointNet on every family of 3D geometries on which the models were tested.
Multi-Objective Multi-Agent Decision Making: A Utility-based Analysis and Survey
We develop a new taxonomy which classifies multi-objective multi-agent decision making settings, on the basis of the reward structures, and which and how utility functions are applied.
Transfer Learning Across Simulated Robots With Different Sensors
After training in the lab, the robot should be able to get by without the expensive equipment that used to be available to it, and yet still be guaranteed to perform well on the field.
Sample-Efficient Model-Free Reinforcement Learning with Off-Policy Critics
We argue that actor-critic algorithms are limited by their need for an on-policy critic.
The Actor-Advisor: Policy Gradient With Off-Policy Advice
In this paper, we propose an elegant solution, the Actor-Advisor architecture, in which a Policy Gradient actor learns from unbiased Monte-Carlo returns, while being shaped (or advised) by the Softmax policy arising from an off-policy critic.
Dynamic Weights in Multi-Objective Deep Reinforcement Learning
In the dynamic weights setting the relative importance changes over time and specialized algorithms that deal with such change, such as a tabular Reinforcement Learning (RL) algorithm by Natarajan and Tadepalli (2005), are required.
Multi-Objective Reinforcement Learning
reinforcement-learning
Directed Policy Gradient for Safe Reinforcement Learning with Human Advice
Our technique, Directed Policy Gradient (DPG), allows a teacher or backup policy to override the agent before it acts undesirably, while allowing the agent to leverage human advice or directives to learn faster.
Learning to Coordinate with Coordination Graphs in Repeated Single-Stage Multi-Agent Decision Problems
Learning to coordinate between multiple agents is an important problem in many reinforcement learning problems.
Ordered Preference Elicitation Strategies for Supporting Multi-Objective Decision Making
We build on previous work on Gaussian processes and pairwise comparisons for preference modelling, extend it to the multi-objective decision support scenario, and propose new ordered preference elicitation strategies based on ranking and clustering.
Bayesian Best-Arm Identification for Selecting Influenza Mitigation Strategies
We evaluate these algorithms in a realistic experimental setting and demonstrate that it is possible to identify the optimal strategy using only a limited number of model evaluations, i. e., 2-to-3 times faster compared to the uniform sampling method, the predominant technique used for epidemiological decision making in the literature.
Reinforcement Learning in POMDPs with Memoryless Options and Option-Observation Initiation Sets
Many real-world reinforcement learning problems have a hierarchical nature, and often exhibit some degree of partial observability.
Analysing Congestion Problems in Multi-agent Reinforcement Learning
Congestion problems are omnipresent in today's complex networks and represent a challenge in many research domains.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Solving stable matching problems using answer set programming
Since the introduction of the stable marriage problem (SMP) by Gale and Shapley (1962), several variants and extensions have been investigated.
Modeling Stable Matching Problems with Answer Set Programming
Our encoding can easily be extended and adapted to the needs of specific applications.
