Perspective Taking in Deep Reinforcement Learning Agents

2019-07-03 · Aqeel Labash, Jaan Aru, Tambet Matiisen, Ardi Tampuu, Raul Vicente

Perspective taking is the ability to take the point of view of another agent. This skill is not unique to humans as it is also displayed by other animals like chimpanzees. It is an essential ability for social interactions, including efficient cooperation, competition, and communication. Here we present our progress toward building artificial agents with such abilities. We implemented a perspective taking task inspired by experiments done with chimpanzees. We show that agents controlled by artificial neural networks can learn via reinforcement learning to pass simple tests that require perspective taking capabilities. We studied whether this ability is more readily learned by agents with information encoded in allocentric or egocentric form for both their visual perception and motor actions. We believe that, in the long run, building better artificial agents with perspective taking ability can help us develop artificial intelligence that is more human-like and easier to communicate with.

📄 PDF Abstract BibTeX arXiv:1907.01851

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement Learningreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

On the Opportunities and Challenges of Offline Reinforcement Learning for Recommender Systems

2023-08-22 · Xiaocong Chen, Siyu Wang, Julian McAuley, Dietmar Jannach 외

Reinforcement learning serves as a potent tool for modeling dynamic user interests within recommender systems, garnering increasing research attention of late. However, a significant drawback persists: its poor data effi…

Recommendation Systems reinforcement-learning Reinforcement Learning

Who Sees What? Structured Thought-Action Sequences for Epistemic Reasoning in LLMs

2025-08-20 · Luca Annese, Sabrina Patania, Silvia Serino, Tom Foulsham 외 arxiv

Recent advances in large language models (LLMs) and reasoning frameworks have opened new possibilities for improving the perspective -taking capabilities of autonomous agents. However, tasks that involve active perceptio…

Epistemic Reasoning

CopyCAT: Taking Control of Neural Policies with Constant Attacks

2019-05-29 · Léonard Hussenot, Matthieu Geist, Olivier Pietquin

We propose a new perspective on adversarial attacks against deep reinforcement learning agents. Our main contribution is CopyCAT, a targeted attack able to consistently lure an agent into following an outsider's policy. …

Atari Games Deep Reinforcement Learning reinforcement-learning Reinforcement Learning+1

SA-MATD3:Self-attention-based multi-agent continuous control method in cooperative environments

2021-07-01 · Kai Liu, Yuyang Zhao, Gang Wang, Bei Peng

Cooperative problems under continuous control have always been the focus of multi-agent reinforcement learning. Existing algorithms suffer from the problem of uneven learning degree with the increase of the number of age…

continuous-control Continuous Control Multi-agent Reinforcement Learning

Emergent Social Learning via Multi-agent Reinforcement Learning

2020-10-01 · Kamal Ndousse, Douglas Eck, Sergey Levine, Natasha Jaques

Social learning is a key component of human and animal intelligence. By taking cues from the behavior of experts in their environment, social learners can acquire sophisticated behavior and rapidly adapt to new circumsta…

Imitation Learning Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning+1