Search Results for author:
Found 77 papers, 27 papers with code
Inferring the Phylogeny of Large Language Models and Predicting their Performances in Benchmarks
This paper introduces PhyloLM, a method applying phylogenetic algorithms to Large Language Models to explore their finetuning relationships, and predict their performance characteristics.
Cultural evolution in populations of Large Language Models
We here present a framework for simulating cultural evolution in populations of LLMs, allowing the manipulation of variables known to be important in cultural evolution, such as network structure, personality, and the way social information is aggregated and transformed.
Stick to your Role! Stability of Personal Values Expressed in Large Language Models
In this paper, we present a case-study about the stability of value expression over different contexts (simulated conversations on different topics), and as measured using a standard psychology questionnaire (PVQ) and a behavioral downstream task.
Discovering Sensorimotor Agency in Cellular Automata using Diversity Search
The research field of Artificial Life studies how life-like phenomena such as autopoiesis, agency, or self-regulation can self-organize in computer simulations.
Improved Performances and Motivation in Intelligent Tutoring Systems: Combining Machine Learning and Learner Choice
In this context, the ZPDES algorithm, based on the Learning Progress Hypothesis (LPH) and multi-armed bandit machine learning techniques, sequences exercises that maximize learning progress (LP).
Meta-Diversity Search in Complex Systems, A Recipe for Artificial Open-Endedness ?
Holmes incrementally learns a hierarchy of modular representations to characterize divergent sources of diversity and uses a goal-based intrinsically-motivated exploration as the diversity search strategy.
ACES: Generating Diverse Programming Puzzles with Autotelic Language Models and Semantic Descriptors
We here study automated problem generation in the context of the open-ended space of python programming puzzles.
SBMLtoODEjax: Efficient Simulation and Optimization of Biological Network Models in JAX
Advances in bioengineering and biomedicine demand a deep understanding of the dynamic behavior of biological systems, ranging from protein pathways to complex cellular processes.
Large Language Models as Superpositions of Cultural Perspectives
We introduce the concept of perspective controllability, which refers to a model's affordance to adopt various perspectives with differing values and personality traits.
The SocialAI School: Insights from Developmental Psychology Towards Artificial Socio-Cultural Agents
Developmental psychologists have long-established the importance of socio-cognitive abilities in human intelligence.
Augmenting Autotelic Agents with Large Language Models
Without relying on any hand-coded goal representations, reward functions or curriculum, we show that LMA3 agents learn to master a large diversity of skills in a task-agnostic text-based environment.
Supporting Qualitative Analysis with Large Language Models: Combining Codebook with GPT-3 for Deductive Coding
In this study, we explored the use of large language models (LLMs) in supporting deductive coding, a major category of qualitative analysis where researchers use pre-determined codebooks to label the data into a fixed set of codes.
A Song of Ice and Fire: Analyzing Textual Autotelic Agents in ScienceWorld
We show the importance of selectivity from the social peer's feedback; that experience replay needs to over-sample examples of rare goals; and that following self-generated goal sequences where the agent's competence is intermediate leads to significant improvements in final performance.
Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning
Using an interactive textual environment designed to study higher-level forms of functional grounding, and a set of spatial and navigation tasks, we study several scientific questions: 1) Can LLMs boost sample efficiency for online learning of various RL tasks?
Flow-Lenia: Towards open-ended evolution in cellular automata through mass conservation and parameter localization
Finally, we show that Flow Lenia enables the integration of the parameters of the CA update rules within the CA dynamics, making them dynamic and localized, allowing for multi-species simulations, with locally coherent update rules that define properties of the emerging creatures, and that can be mixed with neighbouring rules.
GPT-3-driven pedagogical agents for training children's curious question-asking skills
In this context, we propose to leverage advances in the natural language processing field (NLP) and investigate the efficiency of using a large language model (LLM) for automating the production of the pedagogical content of a curious question-asking (QA) training.
Contrastive Multimodal Learning for Emergence of Graphical Sensory-Motor Communication
In this paper, we investigate whether artificial agents can develop a shared language in an ecological setting where communication relies on a sensory-motor channel.
Selecting Better Samples from Pre-trained LLMs: A Case Study on Question Generation
Large Language Models (LLMs) have in recent years demonstrated impressive prowess in natural language generation.
Automatic Exploration of Textual Environments with Language-Conditioned Autotelic Agents
In this extended abstract we discuss the opportunities and challenges of studying intrinsically-motivated agents for exploration in textual environments.
EAGER: Asking and Answering Questions for Automatic Reward Shaping in Language-guided RL
Reinforcement learning (RL) in long horizon and sparse reward tasks is notoriously difficult and requires a lot of training steps.
Social Network Structure Shapes Innovation: Experience-sharing in RL with SAPIENS
Comparing the level of innovation achieved by different social network structures across different tasks shows that, first, consistent with human findings, experience sharing within a dynamic structure achieves the highest level of innovation in tasks with a deceptive nature and large search spaces.
Cultural Vocal Bursts Intensity Prediction
Reinforcement Learning (RL)
Language and Culture Internalisation for Human-Like Autotelic AI
Building autonomous agents able to grow open-ended repertoires of skills across their lives is a fundamental goal of artificial intelligence (AI).
Asking for Knowledge: Training RL Agents to Query External Knowledge Using Language
In order to study how agents can be taught to query external knowledge via language, we first introduce two new environments: the grid-world-based Q-BabyAI and the text-based Q-TextWorld.
Language-biased image classification: evaluation based on semantic representations
This suggests that the semantic word representation in the CLIP visual processing is not shared with the image representation, although the word representation strongly dominates for word-embedded images.
Learning to Guide and to Be Guided in the Architect-Builder Problem
ABIG results in a low-level, high-frequency, guiding communication protocol that not only enables an architect-builder pair to solve the task at hand, but that can also generalize to unseen tasks.
Evaluating Language-biased image classification based on semantic compositionality
This suggests that the semantic word representation in the CLIP visual processing is not shared with the image representation, although the word representation strongly dominates for word-embedded images.
SocialAI: Benchmarking Socio-Cognitive Abilities in Deep Reinforcement Learning Agents
In this paper, we argue that aiming towards human-level AI requires a broader set of key social skills: 1) language use in complex and variable social contexts; 2) beyond language, complex embodied communication in multimodal settings within constantly evolving social worlds.
Causal Reinforcement Learning using Observational and Interventional Data
We then ask the following questions: can the online and offline experiences be safely combined for learning a causal model ?
Transflower: probabilistic autoregressive dance generation with multimodal attention
First, we present a novel probabilistic autoregressive architecture that models the distribution over future poses with a normalizing flow conditioned on previous poses as well as music context, using a multimodal transformer encoder.
Grounding Spatio-Temporal Language with Transformers
While there is an extended literature studying how machines can learn grounded language, the topic of how to learn spatio-temporal linguistic concepts is still largely uncharted.
Towards Teachable Autotelic Agents
In the field of Artificial Intelligence, these extremes respectively map to autonomous agents learning from their own signals and interactive learning agents fully taught by their teachers.
SocialAI 0.1: Towards a Benchmark to Stimulate Research on Socio-Cognitive Abilities in Deep Reinforcement Learning Agents
Building embodied autonomous agents capable of participating in social interactions with humans is one of the main challenges in AI.
TeachMyAgent: a Benchmark for Automatic Curriculum Learning in Deep RL
Training autonomous agents able to generalize to multiple tasks is a key target of Deep Reinforcement Learning (DRL) research.
Intelligent behavior depends on the ecological niche: Scaling up AI to human-like intelligence in socio-cultural environments
This paper outlines a perspective on the future of AI, discussing directions for machines models of human-like intelligence.
Autotelic Agents with Intrinsically Motivated Goal-Conditioned Reinforcement Learning: a Short Survey
Developmental RL is concerned with the use of deep RL algorithms to tackle a developmental problem -- the $intrinsically$ $motivated$ $acquisition$ $of$ $open$-$ended$ $repertoires$ $of$ $skills$.
Language as a Cognitive Tool to Imagine Goals in Curiosity Driven Exploration
We argue that the ability to imagine out-of-distribution goals is key to enable creative discoveries and open-ended learning.
Meta Automatic Curriculum Learning
In such complex task spaces, it is essential to rely on some form of Automatic Curriculum Learning (ACL) to adapt the task sampling distribution to a given learning agent, instead of randomly sampling tasks, as many could end up being either trivial or unfeasible.
EpidemiOptim: A Toolbox for the Optimization of Control Policies in Epidemiological Models
Epidemiologists model the dynamics of epidemics in order to propose control strategies based on pharmaceutical and non-pharmaceutical interventions (contact limitation, lock down, vaccination, etc).
GRIMGEP: Learning Progress for Robust Goal Sampling in Visual Deep Reinforcement Learning
However, a currently known limitation of agents trying to maximize the diversity of sampled goals is that they tend to get attracted to noise or more generally to parts of the environments that cannot be controlled (distractors).
Hierarchically Organized Latent Modules for Exploratory Search in Morphogenetic Systems
Self-organization of complex morphological patterns from local interactions is a fascinating phenomenon in many natural and artificial systems.
Language-Conditioned Goal Generation: a New Approach to Language Grounding in RL
In the real world, linguistic agents are also embodied agents: they perceive and act in the physical world.
Language-Goal Imagination to Foster Creative Exploration in Deep RL
We introduce the Playground environment and study how this form of goal imagination improves generalization and exploration over agents lacking this capacity.
Language-Conditioned Goal Generation: a New Approach to Language Grounding for RL
In the real world, linguistic agents are also embodied agents: they perceive and act in the physical world.
Grounding Language to Autonomously-Acquired Skills via Goal Generation
In a second stage (L -> G), it trains a language-conditioned goal generator to generate semantic goals that match the constraints expressed in language-based inputs.
Progressive growing of self-organized hierarchical representations for exploration
A central challenge is how to learn incrementally representations in order to progressively build a map of the discovered structures and re-use it to further explore.
SpatialSim: Recognizing Spatial Configurations of Objects with Graph Neural Networks
Recognizing precise geometrical configurations of groups of objects is a key capability of human spatial cognition, yet little studied in the deep learning literature so far.
Trying AGAIN instead of Trying Longer: Prior Learning for Automatic Curriculum Learning
A major challenge in the Deep RL (DRL) community is to train agents able to generalize over unseen situations, which is often approached by training them on a diversity of tasks (or environments).
Automatic Curriculum Learning For Deep RL: A Short Survey
Automatic Curriculum Learning (ACL) has become a cornerstone of recent successes in Deep Reinforcement Learning (DRL). These methods shape the learning trajectories of agents by challenging them with tasks adapted to their capacities.
Language as a Cognitive Tool to Imagine Goals in Curiosity-Driven Exploration
We argue that the ability to imagine out-of-distribution goals is key to enable creative discoveries and open-ended learning.
Multi-Agent Reinforcement Learning as a Computational Tool for Language Evolution Research: Historical Context and Future Challenges
Computational models of emergent communication in agent populations are currently gaining interest in the machine learning community due to recent advances in Multi-Agent Reinforcement Learning (MARL).
BIG-bench Machine Learning
Multi-agent Reinforcement Learning
+3
User-in-the-loop Adaptive Intent Detection for Instructable Digital Assistant
To provide such functionalities, NL interpretation in traditional assistants should be improved: (1) The intent identification system should be able to recognize new forms of known intents, and to acquire new intents as they are expressed by the user.
Language Grounding through Social Interactions and Curiosity-Driven Multi-Goal Learning
We propose LE2 (Language Enhanced Exploration), a learning algorithm leveraging intrinsic motivations and natural language (NL) interactions with a descriptive social partner (SP).
Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environments
We consider the problem of how a teacher algorithm can enable an unknown Deep Reinforcement Learning (DRL) student to become good at a skill over a wide range of diverse environments.
Intrinsically Motivated Discovery of Diverse Patterns in Self-Organizing Systems
Using a continuous GOL as a testbed, we show that recent intrinsically-motivated machine learning algorithms (POP-IMGEPs), initially developed for learning of inverse models in robotics, can be transposed and used in this novel application area.
Autonomous Goal Exploration using Learned Goal Spaces for Visuomotor Skill Acquisition in Robots
The automatic and efficient discovery of skills, without supervision, for long-living autonomous agents, remains a challenge of Artificial Intelligence.
A Hitchhiker's Guide to Statistical Comparisons of Reinforcement Learning Algorithms
Consistently checking the statistical significance of experimental results is the first mandatory step towards reproducible science.
Computational and Robotic Models of Early Language Development: A Review
Keywords: Early language learning, Computational and robotic models, machine learning, development, embodiment, social interaction, intrinsic motivation, self-organization, dynamical systems, complexity.
CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learning
In open-ended environments, autonomous learning agents must set their own goals and build their own curriculum through an intrinsically motivated exploration.
Diversity-Driven Selection of Exploration Strategies in Multi-Armed Bandits
We consider a scenario where an agent has multiple available strategies to explore an unknown environment.
Curiosity Driven Exploration of Learned Disentangled Goal Spaces
Finally, we show that the measure of learning progress, used to drive curiosity-driven exploration, can be used simultaneously to discover abstract independently controllable features of the environment.
Accuracy-based Curriculum Learning in Deep Reinforcement Learning
In this paper, we investigate a new form of automated curriculum learning based on adaptive selection of accuracy requirements, called accuracy-based curriculum learning.
How Many Random Seeds? Statistical Power Analysis in Deep Reinforcement Learning Experiments
Consistently checking the statistical significance of experimental results is one of the mandatory methodological steps to address the so-called "reproducibility crisis" in deep reinforcement learning.
Complexity Reduction in the Negotiation of New Lexical Conventions
We define here a new principled measure and a new strategy, based on the beliefs of each agent on the global state of the population.
Socially Guided Intrinsic Motivation for Robot Learning of Motor Skills
This paper presents a technical approach to robot learning of motor skills which combines active intrinsically motivated learning with imitation learning.
Active choice of teachers, learning strategies and goals for a socially guided intrinsic motivation learner
It has to choose actively and hierarchically at each learning episode: 1) what to learn: which outcome is most interesting to select as a goal to focus on for goal-directed exploration; 2) how to learn: which data collection strategy to use among self-exploration, mimicry and emulation; 3) once he has decided when and what to imitate by choosing mimicry or emulation, then he has to choose who to imitate, from a set of different teachers.
Unsupervised Learning of Goal Spaces for Intrinsically Motivated Goal Exploration
Intrinsically motivated goal exploration algorithms enable machines to discover repertoires of policies that produce a diversity of effects in complex environments.
Computational Theories of Curiosity-Driven Learning
What are the mechanisms of curiosity-driven learning?
GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms
In continuous action domains, standard deep reinforcement learning algorithms like DDPG suffer from inefficient exploration when facing sparse or deceptive reward problems.
Proximodistal Exploration in Motor Learning as an Emergent Property of Optimization
Here, we formulate and study computationally the hypothesis that such patterns can emerge spontaneously as the result of a family of stochastic optimization processes (evolution strategies with covariance-matrix adaptation), without an innate encoding of a maturational schedule.
Autonomous development and learning in artificial intelligence and robotics: Scaling up deep learning to human--like learning
Autonomous lifelong development and learning is a fundamental capability of humans, differentiating them from current deep learning systems.
Intrinsically Motivated Goal Exploration Processes with Automatic Curriculum Learning
We present an algorithmic approach called Intrinsically Motivated Goal Exploration Processes (IMGEP) to enable similar properties of autonomous learning in machines.
Open challenges in understanding development and evolution of speech forms: The roles of embodied self-organization, motivation and active exploration
This article discusses open scientific challenges for understanding development and evolution of speech forms, as a commentary to Moulin-Frier et al. (Moulin-Frier et al., 2015).
What do we learn about development from baby robots?
To address this challenge, building and experimenting with robots modeling the growing infant brain and body is crucial.
Multi-Armed Bandits for Intelligent Tutoring Systems
We present an approach to Intelligent Tutoring Systems which adaptively personalizes sequences of learning activities to maximize skills acquired by students, taking into account the limited time and motivational resources.
Active Learning of Inverse Models with Intrinsically Motivated Goal Exploration in Robots
The architecture makes the robot sample actively novel parameterized tasks in the task space, based on a measure of competence progress, each of which triggers low-level goal-directed learning of the motor policy pa- rameters that allow to solve it.
Exploration in Model-based Reinforcement Learning by Empirically Estimating Learning Progress
Formal exploration approaches in model-based reinforcement learning estimate the accuracy of the currently learned model without consideration of the empirical prediction error.
Model-based Reinforcement Learning
reinforcement-learning
+1
