Search Results for author:
Found 56 papers, 22 papers with code
A tale of two goals: leveraging sequentiality in multi-goal scenarios
In the first, the agent is conditioned on both the current and final goals, while in the second, it is conditioned on the next two goals in the sequence.
VIPER: Visual Perception and Explainable Reasoning for Sequential Decision-Making
While Large Language Models (LLMs) excel at reasoning on text and Vision-Language Models (VLMs) are highly effective for visual perception, applying those models for visual instruction-based planning remains a widely open problem.
MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces
Open-ended learning agents must efficiently prioritize goals in vast possibility spaces, focusing on those that maximize learning progress (LP).
Reinforcement Learning for Aligning Large Language Models Agents with Interactive Environments: Quantifying and Mitigating Prompt Overfitting
Finally, we propose to use a contrastive loss to mitigate this sensitivity and improve the robustness and generalization capabilities of LLMs.
SAC-GLAM: Improving Online RL for LLM agents with Soft Actor-Critic and Hindsight Relabeling
The past years have seen Large Language Models (LLMs) strive not only as generative models but also as agents solving textual sequential decision-making tasks.
From Goal-Conditioned to Language-Conditioned Agents via Vision-Language Models
Vision-language models (VLMs) have tremendous potential for grounding language, and thus enabling language-conditioned agents (LCAs) to perform diverse tasks specified with text.
Physics-Informed Model and Hybrid Planning for Efficient Dyna-Style Reinforcement Learning
Applying reinforcement learning (RL) to real-world applications requires addressing a trade-off between asymptotic performance, sample efficiency, and inference time.
Single-Reset Divide & Conquer Imitation Learning
Demonstrations are commonly used to speed up the learning process of Deep Reinforcement Learning algorithms.
A Definition of Open-Ended Learning Problems for Goal-Conditioned Agents
A lot of recent machine learning research papers have ``open-ended learning'' in their title.
Utility-based Adaptive Teaching Strategies using Bayesian Theory of Mind
To this end, human teachers seem to build mental models of the learner's internal state, a capacity known as Theory of Mind (ToM).
Enhancing Agent Communication and Learning through Action and Language
We introduce a novel category of GC-agents capable of functioning as both teachers and learners.
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?
Leveraging Sequentiality in Reinforcement Learning from a Single Demonstration
This sequential goal-reaching approach raises a problem of compatibility between successive goals: we need to ensure that the state resulting from reaching a goal is compatible with the achievement of the following goals.
Overcoming Referential Ambiguity in Language-Guided Goal-Conditioned Reinforcement Learning
Teaching an agent to perform new tasks using natural language can easily be hindered by ambiguities in interpretation.
Making Reinforcement Learning Work on Swimmer
A lot of these papers report poor performance on SWIMMER from RL methods and much better performance from direct policy search methods.
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.
Stein Variational Goal Generation for adaptive Exploration in Multi-Goal Reinforcement Learning
In multi-goal Reinforcement Learning, an agent can share experience between related training tasks, resulting in better generalization for new tasks at test time.
Pragmatically Learning from Pedagogical Demonstrations in Multi-Goal Environments
In this paper, we implement pedagogy and pragmatism mechanisms by leveraging a Bayesian model of Goal Inference from demonstrations (BGI).
Divide & Conquer Imitation Learning
In such context, Imitation Learning (IL) can be a powerful approach to bootstrap the learning process.
Learning Object-Centered Autotelic Behaviors with Graph Neural Networks
However, these capabilities are highly constrained by their policy and goal space representations.
Combining Evolution and Deep Reinforcement Learning for Policy Search: a Survey
Deep neuroevolution and deep Reinforcement Learning have received a lot of attention in the last years.
Pedagogical Demonstrations and Pragmatic Learning in Artificial Tutor-Learner Interactions
When demonstrating a task, human tutors pedagogically modify their behavior by either "showing" the task rather than just "doing" it (exaggerating on relevant parts of the demonstration) or by giving demonstrations that best disambiguate the communicated goal.
Help Me Explore: Minimal Social Interventions for Graph-Based Autotelic Agents
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
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.
Selection-Expansion: A Unifying Framework for Motion-Planning and Diversity Search Algorithms
In particular, we show empirically that, if the mapping is smooth enough, i. e. if two close policies in the parameter space lead to similar outcomes, then diversity algorithms tend to inherit exploration properties of MP algorithms.
Factored Action Spaces in Deep Reinforcement Learning
Very large action spaces constitute a critical challenge for deep Reinforcement Learning (RL) algorithms.
Sample efficient Quality Diversity for neural continuous control
The QD part contributes structural biases by decoupling the search for diversity from the search for high return, resulting in efficient management of the exploration-exploitation trade-off.
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 $intrinsically$ $motivated$ $acquisition$ $of$ $open$-$ended$ $repertoires$ $of$ $skills$.
Offline Reinforcement Learning Hands-On
Offline Reinforcement Learning (RL) aims to turn large datasets into powerful decision-making engines without any online interactions with the environment.
Learning Compositional Neural Programs for Continuous Control
Third, the self-models are harnessed to learn recursive compositional programs with multiple levels of abstraction.
Diversity Policy Gradient for Sample Efficient Quality-Diversity Optimization
This paper proposes a novel algorithm, QDPG, which combines the strength of Policy Gradient algorithms and Quality Diversity approaches to produce a collection of diverse and high-performing neural policies in continuous control environments.
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-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.
DREAM Architecture: a Developmental Approach to Open-Ended Learning in Robotics
Robots are still limited to controlled conditions, that the robot designer knows with enough details to endow the robot with the appropriate models or behaviors.
PBCS : Efficient Exploration and Exploitation Using a Synergy between Reinforcement Learning and Motion Planning
In this paper, we propose a new algorithm called "Plan, Backplay, Chain Skills" (PBCS) that combines motion planning and reinforcement learning to solve hard exploration environments.
To Share or Not To Share: A Comprehensive Appraisal of Weight-Sharing
Weight-sharing (WS) has recently emerged as a paradigm to accelerate the automated search for efficient neural architectures, a process dubbed Neural Architecture Search (NAS).
The problem with DDPG: understanding failures in deterministic environments with sparse rewards
In environments with continuous state and action spaces, state-of-the-art actor-critic reinforcement learning algorithms can solve very complex problems, yet can also fail in environments that seem trivial, but the reason for such failures is still poorly understood.
Learning Compositional Neural Programs with Recursive Tree Search and Planning
AlphaZero contributes powerful neural network guided search algorithms, which we augment with recursion.
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.
Investigating Generalisation in Continuous Deep Reinforcement Learning
Deep Reinforcement Learning has shown great success in a variety of control tasks.
Interactively shaping robot behaviour with unlabeled human instructions
In this paper, we propose a framework that enables a human teacher to shape a robot behaviour by interactively providing it with unlabeled instructions.
CLIC: Curriculum Learning and Imitation for object Control in non-rewarding environments
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.
First-order and second-order variants of the gradient descent in a unified framework
In this paper, we provide an overview of first-order and second-order variants of the gradient descent method that are commonly used in machine learning.
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.
Identification of Invariant Sensorimotor Structures as a Prerequisite for the Discovery of Objects
Our model is based on processing the unsupervised interaction of an artificial agent with its environment.
CEM-RL: Combining evolutionary and gradient-based methods for policy search
In this paper, we propose a different combination scheme using the simple cross-entropy method (CEM) and Twin Delayed Deep Deterministic policy gradient (td3), another off-policy deep RL algorithm which improves over ddpg.
Importance mixing: Improving sample reuse in evolutionary policy search methods
Then, from an empirical comparison based on a simple benchmark, we show that, though it actually provides better sample efficiency, it is still far from the sample efficiency of deep reinforcement learning, though it is more stable.
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.
Policy Search in Continuous Action Domains: an Overview
Continuous action policy search is currently the focus of intensive research, driven both by the recent success of deep reinforcement learning algorithms and the emergence of competitors based on evolutionary algorithms.
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.
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.
Actor-critic versus direct policy search: a comparison based on sample complexity
Sample efficiency is a critical property when optimizing policy parameters for the controller of a robot.
Gated networks: an inventory
Gated networks are networks that contain gating connections, in which the outputs of at least two neurons are multiplied.
Path Integral Policy Improvement with Covariance Matrix Adaptation
There has been a recent focus in reinforcement learning on addressing continuous state and action problems by optimizing parameterized policies.
