Search Results for author: Cédric Colas

Found 25 papers, 12 papers with code

Large Language Models as Superpositions of Cultural Perspectives

no code implementations15 Jul 2023 Grgur Kovač, Masataka Sawayama, Rémy Portelas, Cédric Colas, Peter Ford Dominey, Pierre-Yves Oudeyer

We introduce the concept of perspective controllability, which refers to a model's affordance to adopt various perspectives with differing values and personality traits.

Augmenting Autotelic Agents with Large Language Models

no code implementations21 May 2023 Cédric Colas, Laetitia Teodorescu, Pierre-Yves Oudeyer, Xingdi Yuan, Marc-Alexandre Côté

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.

Common Sense Reasoning Language Modelling

Language and Culture Internalisation for Human-Like Autotelic AI

no code implementations2 Jun 2022 Cédric Colas, Tristan Karch, Clément Moulin-Frier, Pierre-Yves Oudeyer

Building autonomous agents able to grow open-ended repertoires of skills across their lives is a fundamental goal of artificial intelligence (AI).

Attribute Cultural Vocal Bursts Intensity Prediction

Help Me Explore: Minimal Social Interventions for Graph-Based Autotelic Agents

1 code implementation10 Feb 2022 Ahmed Akakzia, Olivier Serris, Olivier Sigaud, Cédric Colas

In the quest for autonomous agents learning open-ended repertoires of skills, most works take a Piagetian perspective: learning trajectories are the results of interactions between developmental agents and their physical environment.

Towards Teachable Autotelic Agents

no code implementations25 May 2021 Olivier Sigaud, Ahmed Akakzia, Hugo Caselles-Dupré, Cédric Colas, Pierre-Yves Oudeyer, Mohamed Chetouani

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.

Autotelic Agents with Intrinsically Motivated Goal-Conditioned Reinforcement Learning: a Short Survey

no code implementations17 Dec 2020 Cédric Colas, Tristan Karch, Olivier Sigaud, Pierre-Yves Oudeyer

Developmental RL is concerned with the use of deep RL algorithms to tackle a developmental problem -- the $intrinsically$ $motivated$ $acquisition$ $of$ $open$-$ended$ $repertoires$ $of$ $skills$.

reinforcement-learning Reinforcement Learning (RL)

EpidemiOptim: A Toolbox for the Optimization of Control Policies in Epidemiological Models

2 code implementations9 Oct 2020 Cédric Colas, Boris Hejblum, Sébastien Rouillon, Rodolphe Thiébaut, Pierre-Yves Oudeyer, Clément Moulin-Frier, Mélanie Prague

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).

Epidemiology Evolutionary Algorithms +5

Language-Goal Imagination to Foster Creative Exploration in Deep RL

no code implementations ICML Workshop LaReL 2020 Tristan Karch, Nicolas Lair, Cédric Colas, Jean-Michel Dussoux, Clément Moulin-Frier, Peter Ford Dominey, Pierre-Yves Oudeyer

We introduce the Playground environment and study how this form of goal imagination improves generalization and exploration over agents lacking this capacity.

Grounding Language to Autonomously-Acquired Skills via Goal Generation

1 code implementation ICLR 2021 Ahmed Akakzia, Cédric Colas, Pierre-Yves Oudeyer, Mohamed Chetouani, Olivier Sigaud

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.

Language Acquisition

Deep Sets for Generalization in RL

no code implementations20 Mar 2020 Tristan Karch, Cédric Colas, Laetitia Teodorescu, Clément Moulin-Frier, Pierre-Yves Oudeyer

This paper investigates the idea of encoding object-centered representations in the design of the reward function and policy architectures of a language-guided reinforcement learning agent.

Navigate Object +3

Automatic Curriculum Learning For Deep RL: A Short Survey

no code implementations10 Mar 2020 Rémy Portelas, Cédric Colas, Lilian Weng, Katja Hofmann, Pierre-Yves Oudeyer

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.

reinforcement-learning Reinforcement Learning (RL)

Scaling MAP-Elites to Deep Neuroevolution

3 code implementations3 Mar 2020 Cédric Colas, Joost Huizinga, Vashisht Madhavan, Jeff Clune

Quality-Diversity (QD) algorithms, and MAP-Elites (ME) in particular, have proven very useful for a broad range of applications including enabling real robots to recover quickly from joint damage, solving strongly deceptive maze tasks or evolving robot morphologies to discover new gaits.

Efficient Exploration

Language Grounding through Social Interactions and Curiosity-Driven Multi-Goal Learning

no code implementations8 Nov 2019 Nicolas Lair, Cédric Colas, Rémy Portelas, Jean-Michel Dussoux, Peter Ford Dominey, Pierre-Yves Oudeyer

We propose LE2 (Language Enhanced Exploration), a learning algorithm leveraging intrinsic motivations and natural language (NL) interactions with a descriptive social partner (SP).

Active Learning Descriptive

Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environments

2 code implementations16 Oct 2019 Rémy Portelas, Cédric Colas, Katja Hofmann, Pierre-Yves Oudeyer

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.

A Hitchhiker's Guide to Statistical Comparisons of Reinforcement Learning Algorithms

2 code implementations15 Apr 2019 Cédric Colas, Olivier Sigaud, Pierre-Yves Oudeyer

Consistently checking the statistical significance of experimental results is the first mandatory step towards reproducible science.

reinforcement-learning Reinforcement Learning (RL)

CLIC: Curriculum Learning and Imitation for object Control in non-rewarding environments

no code implementations28 Jan 2019 Pierre Fournier, Olivier Sigaud, Cédric Colas, Mohamed Chetouani

In this paper we study a new reinforcement learning setting where the environment is non-rewarding, contains several possibly related objects of various controllability, and where an apt agent Bob acts independently, with non-observable intentions.

reinforcement-learning Reinforcement Learning (RL) +1

CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learning

1 code implementation15 Oct 2018 Cédric Colas, Pierre Fournier, Olivier Sigaud, Mohamed Chetouani, Pierre-Yves Oudeyer

In open-ended environments, autonomous learning agents must set their own goals and build their own curriculum through an intrinsically motivated exploration.

Efficient Exploration Multi-Goal Reinforcement Learning +2

How Many Random Seeds? Statistical Power Analysis in Deep Reinforcement Learning Experiments

1 code implementation21 Jun 2018 Cédric Colas, Olivier Sigaud, Pierre-Yves Oudeyer

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.

reinforcement-learning Reinforcement Learning (RL)

GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms

1 code implementation ICML 2018 Cédric Colas, Olivier Sigaud, Pierre-Yves Oudeyer

In continuous action domains, standard deep reinforcement learning algorithms like DDPG suffer from inefficient exploration when facing sparse or deceptive reward problems.

reinforcement-learning Reinforcement Learning (RL)

Cannot find the paper you are looking for? You can Submit a new open access paper.