Search Results for author:
Found 25 papers, 9 papers with code
Learning from Explanations and Demonstrations: A Pilot Study
AI has become prominent in a growing number of systems, and, as a direct consequence, the desire for explainability in such systems has become prominent as well.
Implicit Repair with Reinforcement Learning in Emergent Communication
Conversational repair is a mechanism used to detect and resolve miscommunication and misinformation problems when two or more agents interact.
Distributed Value Decomposition Networks with Networked Agents
We investigate the problem of distributed training under partial observability, whereby cooperative multi-agent reinforcement learning agents (MARL) maximize the expected cumulative joint reward.
Networked Agents in the Dark: Team Value Learning under Partial Observability
We propose a novel cooperative multi-agent reinforcement learning (MARL) approach for networked agents.
The Number of Trials Matters in Infinite-Horizon General-Utility Markov Decision Processes
We show that, as opposed to standard MDPs, the number of trials plays a key-role in infinite-horizon GUMDPs and the expected performance of a given policy depends, in general, on the number of trials.
NeuralSolver: Learning Algorithms For Consistent and Efficient Extrapolation Across General Tasks
We contribute NeuralSolver, a novel recurrent solver that can efficiently and consistently extrapolate, i. e., learn algorithms from smaller problems (in terms of observation size) and execute those algorithms in large problems.
Making Friends in the Dark: Ad Hoc Teamwork Under Partial Observability
This paper introduces a formal definition of the setting of ad hoc teamwork under partial observability and proposes a first-principled model-based approach which relies only on prior knowledge and partial observations of the environment in order to perform ad hoc teamwork.
Multi-Bellman operator for convergence of $Q$-learning with linear function approximation
By exploring the properties of this operator, we identify conditions under which the projected multi-Bellman operator becomes contractive, providing improved fixed-point guarantees compared to the Bellman operator.
Interactively Teaching an Inverse Reinforcement Learner with Limited Feedback
In particular, we focus on the situation when the teacher has no access to the learner's model and policy, and the feedback from the learner is limited to trajectories that start from states selected by the teacher.
Learning to Perceive in Deep Model-Free Reinforcement Learning
We investigate whether a model with these characteristics is capable of achieving similar performance to state-of-the-art model-free RL agents that access the full input observation.
Centralized Training with Hybrid Execution in Multi-Agent Reinforcement Learning
We introduce hybrid execution in multi-agent reinforcement learning (MARL), a new paradigm in which agents aim to successfully complete cooperative tasks with arbitrary communication levels at execution time by taking advantage of information-sharing among the agents.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
"Guess what I'm doing": Extending legibility to sequential decision tasks
In this paper we investigate the notion of legibility in sequential decision tasks under uncertainty.
Geometric Multimodal Contrastive Representation Learning
Learning representations of multimodal data that are both informative and robust to missing modalities at test time remains a challenging problem due to the inherent heterogeneity of data obtained from different channels.
Learning Collective Action under Risk Diversity
In this paper we investigate the consequences of risk diversity in groups of agents learning to play CRDs.
Assisting Unknown Teammates in Unknown Tasks: Ad Hoc Teamwork under Partial Observability
In this paper, we present a novel Bayesian online prediction algorithm for the problem setting of ad hoc teamwork under partial observability (ATPO), which enables on-the-fly collaboration with unknown teammates performing an unknown task without needing a pre-coordination protocol.
The Impact of Data Distribution on Q-learning with Function Approximation
We provide a unified theoretical and empirical analysis as to how different properties of the data distribution influence the performance of Q-learning-based algorithms.
How to Sense the World: Leveraging Hierarchy in Multimodal Perception for Robust Reinforcement Learning Agents
This work addresses the problem of sensing the world: how to learn a multimodal representation of a reinforcement learning agent's environment that allows the execution of tasks under incomplete perceptual conditions.
Limited depth bandit-based strategy for Monte Carlo planning in continuous action spaces
This paper addresses the problem of optimal control using search trees.
A Methodology for the Development of RL-Based Adaptive Traffic Signal Controllers
Our methodology addresses the lack of standardization in the literature that renders the comparison of approaches in different works meaningless, due to differences in metrics, environments, and even experimental design and methodology.
A new convergent variant of Q-learning with linear function approximation
In this work, we identify a novel set of conditions that ensure convergence with probability 1 of Q-learning with linear function approximation, by proposing a two time-scale variation thereof.
A Game AI Competition to foster Collaborative AI research and development
In this document, we present the Geometry Friends Game AI Competition.
MHVAE: a Human-Inspired Deep Hierarchical Generative Model for Multimodal Representation Learning
Humans are able to create rich representations of their external reality.
Playing Games in the Dark: An approach for cross-modality transfer in reinforcement learning
In this work we explore the use of latent representations obtained from multiple input sensory modalities (such as images or sounds) in allowing an agent to learn and exploit policies over different subsets of input modalities.
Multi-task Learning and Catastrophic Forgetting in Continual Reinforcement Learning
The first hypothesis is driven by the question of whether a deep reinforcement learning algorithm, trained on two similar tasks, is able to outperform two single-task, individually trained algorithms, by more efficiently learning a new, similar task, that none of the three algorithms has encountered before.
Learning multimodal representations for sample-efficient recognition of human actions
In this work we present \textit{motion concepts}, a novel multimodal representation of human actions in a household environment.
