Search Results for author:
Found 54 papers, 21 papers with code
OPtions as REsponses: Grounding behavioural hierarchies in multi-agent reinforcement learning
This paper investigates generalisation in multi-agent games, where the generality of the agent can be evaluated by playing against opponents it hasn't seen during training.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Framework-Based Qualitative Analysis of Free Responses of Large Language Models: Algorithmic Fidelity
Here we consider whether artificial "silicon participants" generated by LLMs may be productively studied using qualitative methods aiming to produce insights that could generalize to real human populations.
Doing the right thing for the right reason: Evaluating artificial moral cognition by probing cost insensitivity
Is it possible to evaluate the moral cognition of complex artificial agents?
Heterogeneous Social Value Orientation Leads to Meaningful Diversity in Sequential Social Dilemmas
In social psychology, Social Value Orientation (SVO) describes an individual's propensity to allocate resources between themself and others.
Diversity Through Exclusion (DTE): Niche Identification for Reinforcement Learning through Value-Decomposition
The algorithm we propose consists of two parts: an agent architecture and a learning rule.
Melting Pot 2.0
Melting Pot is a research tool developed to facilitate work on multi-agent artificial intelligence, and provides an evaluation protocol that measures generalization to novel social partners in a set of canonical test scenarios.
The emergence of division of labor through decentralized social sanctioning
Here we show that by introducing a model of social norms, which we regard as emergent patterns of decentralized social sanctioning, it becomes possible for groups of self-interested individuals to learn a productive division of labor involving all critical roles.
Emergent Bartering Behaviour in Multi-Agent Reinforcement Learning
Agents learn to produce resources in a spatially complex world, trade them with one another, and consume those that they prefer.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Hidden Agenda: a Social Deduction Game with Diverse Learned Equilibria
A key challenge in the study of multiagent cooperation is the need for individual agents not only to cooperate effectively, but to decide with whom to cooperate.
Statistical discrimination in learning agents
Undesired bias afflicts both human and algorithmic decision making, and may be especially prevalent when information processing trade-offs incentivize the use of heuristics.
Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot
Existing evaluation suites for multi-agent reinforcement learning (MARL) do not assess generalization to novel situations as their primary objective (unlike supervised-learning benchmarks).
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Meta-control of social learning strategies
Based on these findings, we hypothesized that meta-control of individual and social learning strategies provides effective and sample-efficient learning in volatile and uncertain environments.
A multi-agent reinforcement learning model of reputation and cooperation in human groups
Collective action demands that individuals efficiently coordinate how much, where, and when to cooperate.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Quantifying the effects of environment and population diversity in multi-agent reinforcement learning
Generalization is a major challenge for multi-agent reinforcement learning.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Modelling Cooperation in Network Games with Spatio-Temporal Complexity
Such systems have local incentives for individuals, whose behavior has an impact on the global outcome for the group.
Open Problems in Cooperative AI
We see opportunity to more explicitly focus on the problem of cooperation, to construct unified theory and vocabulary, and to build bridges with adjacent communities working on cooperation, including in the natural, social, and behavioural sciences.
DeepMind Lab2D
We present DeepMind Lab2D, a scalable environment simulator for artificial intelligence research that facilitates researcher-led experimentation with environment design.
Negotiating Team Formation Using Deep Reinforcement Learning
When autonomous agents interact in the same environment, they must often cooperate to achieve their goals.
Learning to Resolve Alliance Dilemmas in Many-Player Zero-Sum Games
Here we argue that a systematic study of many-player zero-sum games is a crucial element of artificial intelligence research.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Social diversity and social preferences in mixed-motive reinforcement learning
Recent research on reinforcement learning in pure-conflict and pure-common interest games has emphasized the importance of population heterogeneity.
Silly rules improve the capacity of agents to learn stable enforcement and compliance behaviors
How can societies learn to enforce and comply with social norms?
Smooth markets: A basic mechanism for organizing gradient-based learners
With the success of modern machine learning, it is becoming increasingly important to understand and control how learning algorithms interact.
Generalization of Reinforcement Learners with Working and Episodic Memory
In this paper, we aim to develop a comprehensive methodology to test different kinds of memory in an agent and assess how well the agent can apply what it learns in training to a holdout set that differs from the training set along dimensions that we suggest are relevant for evaluating memory-specific generalization.
Options as responses: Grounding behavioural hierarchies in multi-agent RL
This paper investigates generalisation in multi-agent games, where the generality of the agent can be evaluated by playing against opponents it hasn't seen during training.
Multi-agent Reinforcement Learning
Reinforcement Learning (RL)
Interval timing in deep reinforcement learning agents
The measurement of time is central to intelligent behavior.
Intrinsic Social Motivation via Causal Influence in Multi-Agent RL
Therefore, we also employ influence to train agents to use an explicit communication channel, and find that it leads to more effective communication and higher collective reward.
Learning Reciprocity in Complex Sequential Social Dilemmas
We analyse the resulting policies to show that the reciprocating agents are strongly influenced by their co-players' behavior.
Autocurricula and the Emergence of Innovation from Social Interaction: A Manifesto for Multi-Agent Intelligence Research
Evolution has produced a multi-scale mosaic of interacting adaptive units.
Malthusian Reinforcement Learning
Here we explore a new algorithmic framework for multi-agent reinforcement learning, called Malthusian reinforcement learning, which extends self-play to include fitness-linked population size dynamics that drive ongoing innovation.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Evolving intrinsic motivations for altruistic behavior
Multi-agent cooperation is an important feature of the natural world.
Multiagent Systems
Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning
We propose a unified mechanism for achieving coordination and communication in Multi-Agent Reinforcement Learning (MARL), through rewarding agents for having causal influence over other agents' actions.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Human-level performance in first-person multiplayer games with population-based deep reinforcement learning
Recent progress in artificial intelligence through reinforcement learning (RL) has shown great success on increasingly complex single-agent environments and two-player turn-based games.
Emergent Communication through Negotiation
We also study communication behaviour in a setting where one agent interacts with agents in a community with different levels of prosociality and show how agent identifiability can aid negotiation.
Unsupervised Predictive Memory in a Goal-Directed Agent
Animals execute goal-directed behaviours despite the limited range and scope of their sensors.
Inequity aversion improves cooperation in intertemporal social dilemmas
Groups of humans are often able to find ways to cooperate with one another in complex, temporally extended social dilemmas.
Kickstarting Deep Reinforcement Learning
Our method places no constraints on the architecture of the teacher or student agents, and it regulates itself to allow the students to surpass their teachers in performance.
Psychlab: A Psychology Laboratory for Deep Reinforcement Learning Agents
Psychlab is a simulated psychology laboratory inside the first-person 3D game world of DeepMind Lab (Beattie et al. 2016).
A multi-agent reinforcement learning model of common-pool resource appropriation
Here we show that deep reinforcement learning can be used instead.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Value-Decomposition Networks For Cooperative Multi-Agent Learning
We study the problem of cooperative multi-agent reinforcement learning with a single joint reward signal.
Ranked #1 on
SMAC+
on Off_Superhard_parallel
Multi-agent Reinforcement Learning
reinforcement-learning
+2
Deep Q-learning from Demonstrations
We present an algorithm, Deep Q-learning from Demonstrations (DQfD), that leverages small sets of demonstration data to massively accelerate the learning process even from relatively small amounts of demonstration data and is able to automatically assess the necessary ratio of demonstration data while learning thanks to a prioritized replay mechanism.
Multi-agent Reinforcement Learning in Sequential Social Dilemmas
We introduce sequential social dilemmas that share the mixed incentive structure of matrix game social dilemmas but also require agents to learn policies that implement their strategic intentions.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
DeepMind Lab
DeepMind Lab is a first-person 3D game platform designed for research and development of general artificial intelligence and machine learning systems.
Learning to reinforcement learn
We unpack these points in a series of seven proof-of-concept experiments, each of which examines a key aspect of deep meta-RL.
Reinforcement Learning with Unsupervised Auxiliary Tasks
We also introduce a novel mechanism for focusing this representation upon extrinsic rewards, so that learning can rapidly adapt to the most relevant aspects of the actual task.
Using Fast Weights to Attend to the Recent Past
Until recently, research on artificial neural networks was largely restricted to systems with only two types of variable: Neural activities that represent the current or recent input and weights that learn to capture regularities among inputs, outputs and payoffs.
Model-Free Episodic Control
State of the art deep reinforcement learning algorithms take many millions of interactions to attain human-level performance.
View-tolerant face recognition and Hebbian learning imply mirror-symmetric neural tuning to head orientation
The primate brain contains a hierarchy of visual areas, dubbed the ventral stream, which rapidly computes object representations that are both specific for object identity and relatively robust against identity-preserving transformations like depth-rotations.
Approximate Hubel-Wiesel Modules and the Data Structures of Neural Computation
This paper describes a framework for modeling the interface between perception and memory on the algorithmic level of analysis.
How Important is Weight Symmetry in Backpropagation?
Gradient backpropagation (BP) requires symmetric feedforward and feedback connections -- the same weights must be used for forward and backward passes.
Ranked #1 on
Handwritten Digit Recognition
on MNIST
(PERCENTAGE ERROR metric)
Unsupervised learning of clutter-resistant visual representations from natural videos
Populations of neurons in inferotemporal cortex (IT) maintain an explicit code for object identity that also tolerates transformations of object appearance e. g., position, scale, viewing angle [1, 2, 3].
Learning invariant representations and applications to face verification
Next, we apply the model to non-affine transformations: as expected, it performs well on face verification tasks requiring invariance to the relatively smooth transformations of 3D rotation-in-depth and changes in illumination direction.
Unsupervised Learning of Invariant Representations in Hierarchical Architectures
It also suggests that the main computational goal of the ventral stream of visual cortex is to provide a hierarchical representation of new objects/images which is invariant to transformations, stable, and discriminative for recognition---and that this representation may be continuously learned in an unsupervised way during development and visual experience.
Can a biologically-plausible hierarchy effectively replace face detection, alignment, and recognition pipelines?
The standard approach to unconstrained face recognition in natural photographs is via a detection, alignment, recognition pipeline.
Why The Brain Separates Face Recognition From Object Recognition
Many studies have uncovered evidence that visual cortex contains specialized regions involved in processing faces but not other object classes.
