7 papers · 1 filter
Risk-Aware General-Utility Markov Decision Processes
Pedro P. Santos, Fábio Vital, Alberto Sardinha +1
We study general-utility Markov decision processes (GUMDPs) with risk-aware objectives. In this framework, an agent aims to optimize a risk measure of the distribution of objective…
Entropic Risk-Aware Monte Carlo Tree Search
Pedro P. Santos, Jacopo Silvestrin, Alberto Sardinha +1
We propose a provably correct Monte Carlo tree search (MCTS) algorithm for solving risk-aware Markov decision processes (MDPs) with entropic risk measure (ERM) objectives. We provi…
Solving General-Utility Markov Decision Processes in the Single-Trial Regime with Online Planning
Pedro P. Santos, Alberto Sardinha, Francisco S. Melo
In this work, we contribute the first approach to solve infinite-horizon discounted general-utility Markov decision processes (GUMDPs) in the single-trial regime, i.e., when the ag…
Implicit Repair with Reinforcement Learning in Emergent Communication
Fábio Vital, Alberto Sardinha, Francisco S. Melo
Conversational repair is a mechanism used to detect and resolve miscommunication and misinformation problems when two or more agents interact. One particular and underexplored form…
Distributed Value Decomposition Networks with Networked Agents
Guilherme S. Varela, Alberto Sardinha, Francisco S. Melo
We investigate the problem of distributed training under partial observability, whereby cooperative multi-agent reinforcement learning agents (MARL) maximize the expected cumulativ…
Networked Agents in the Dark: Team Value Learning under Partial Observability
Guilherme S. Varela, Alberto Sardinha, Francisco S. Melo
We propose a novel cooperative multi-agent reinforcement learning (MARL) approach for networked agents. In contrast to previous methods that rely on complete state information or j…
The Number of Trials Matters in Infinite-Horizon General-Utility Markov Decision Processes
Pedro P. Santos, Alberto Sardinha, Francisco S. Melo
The general-utility Markov decision processes (GUMDPs) framework generalizes the MDPs framework by considering objective functions that depend on the frequency of visitation of sta…