Search Results for author:
Found 10 papers, 0 papers with code
On the Sample Efficiency of Abstractions and Potential-Based Reward Shaping in Reinforcement Learning
The use of Potential Based Reward Shaping (PBRS) has shown great promise in the ongoing research effort to tackle sample inefficiency in Reinforcement Learning (RL).
On Computing Plans with Uniform Action Costs
In many real-world planning applications, agents might be interested in finding plans whose actions have costs that are as uniform as possible.
Generalising Planning Environment Redesign
Most research on planning environment (re)design assumes the interested party's objective is to facilitate the recognition of goals and plans, and search over the space of environment modifications to find the minimal set of changes that simplify those tasks and optimise a particular metric.
Contrastive Explanations of Centralized Multi-agent Optimization Solutions
We propose CMAoE, a domain-independent approach to obtain contrastive explanations by: (i) generating a new solution $S^\prime$ where property $P$ is enforced, while also minimizing the differences between $S$ and $S^\prime$; and (ii) highlighting the differences between the two solutions, with respect to the features of the objective function of the multi-agent system.
Fairness in Multi-Agent Planning
In cooperative Multi-Agent Planning (MAP), a set of goals has to be achieved by a set of agents.
Inapplicable Actions Learning for Knowledge Transfer in Reinforcement Learning
Knowing this information can help reduce the sample complexity of RL algorithms by masking the inapplicable actions from the policy distribution to only explore actions relevant to finding an optimal policy.
Anticipatory Counterplanning
In competitive environments, commonly agents try to prevent opponents from achieving their goals.
Explaining Preference-driven Schedules: the EXPRES Framework
The EXPRES framework consists of: (i) an explanation generator that, based on a Mixed-Integer Linear Programming model, finds the best set of reasons that can explain an unsatisfied preference; and (ii) an explanation parser, which translates the generated explanations into human interpretable ones.
Multi-tier Automated Planning for Adaptive Behavior (Extended Version)
A planning domain, as any model, is never complete and inevitably makes assumptions on the environment's dynamic.
Error Analysis and Correction for Weighted A*'s Suboptimality (Extended Version)
There is broad consensus that this bound is not very accurate, that the actual suboptimality of wA*'s solution is often much less than W times optimal.
