Ai alignment: A comprehensive survey

J Ji, T Qiu, B Chen, B Zhang, H Lou, K Wang… - arxiv preprint arxiv …, 2023‏ - arxiv.org
AI alignment aims to make AI systems behave in line with human intentions and values. As
AI systems grow more capable, so do risks from misalignment. To provide a comprehensive …

Autonomous agents modelling other agents: A comprehensive survey and open problems

SV Albrecht, P Stone - Artificial Intelligence, 2018‏ - Elsevier
Much research in artificial intelligence is concerned with the development of autonomous
agents that can interact effectively with other agents. An important aspect of such agents is …

Collaborating with humans without human data

DJ Strouse, K McKee, M Botvinick… - Advances in …, 2021‏ - proceedings.neurips.cc
Collaborating with humans requires rapidly adapting to their individual strengths,
weaknesses, and preferences. Unfortunately, most standard multi-agent reinforcement …

A survey and critique of multiagent deep reinforcement learning

P Hernandez-Leal, B Kartal, ME Taylor - Autonomous Agents and Multi …, 2019‏ - Springer
Deep reinforcement learning (RL) has achieved outstanding results in recent years. This has
led to a dramatic increase in the number of applications and methods. Recent works have …

Benchmarking multi-agent deep reinforcement learning algorithms in cooperative tasks

G Papoudakis, F Christianos, L Schäfer… - arxiv preprint arxiv …, 2020‏ - arxiv.org
Multi-agent deep reinforcement learning (MARL) suffers from a lack of commonly-used
evaluation tasks and criteria, making comparisons between approaches difficult. In this work …

Shared experience actor-critic for multi-agent reinforcement learning

F Christianos, L Schäfer… - Advances in neural …, 2020‏ - proceedings.neurips.cc
Exploration in multi-agent reinforcement learning is a challenging problem, especially in
environments with sparse rewards. We propose a general method for efficient exploration by …

A survey of learning in multiagent environments: Dealing with non-stationarity

P Hernandez-Leal, M Kaisers, T Baarslag… - arxiv preprint arxiv …, 2017‏ - arxiv.org
The key challenge in multiagent learning is learning a best response to the behaviour of
other agents, which may be non-stationary: if the other agents adapt their strategy as well …

Scaling multi-agent reinforcement learning with selective parameter sharing

F Christianos, G Papoudakis… - International …, 2021‏ - proceedings.mlr.press
Sharing parameters in multi-agent deep reinforcement learning has played an essential role
in allowing algorithms to scale to a large number of agents. Parameter sharing between …

A survey of ad hoc teamwork research

R Mirsky, I Carlucho, A Rahman, E Fosong… - European conference on …, 2022‏ - Springer
Ad hoc teamwork is the research problem of designing agents that can collaborate with new
teammates without prior coordination. This survey makes a two-fold contribution: First, it …

Making friends on the fly: Cooperating with new teammates

S Barrett, A Rosenfeld, S Kraus, P Stone - Artificial Intelligence, 2017‏ - Elsevier
Robots are being deployed in an increasing variety of environments for longer periods of
time. As the number of robots grows, they will increasingly need to interact with other robots …