Image de couverture de livre

From Parameters to Behaviors: Unsupervised Compression of the Policy Space

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Tenedini, Davide, Zamboni, Riccardo, Mutti, Mirco, Restelli, Marcello
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Unsupervised Behavioral Compression: Learning Low-Dimensional Policy Manifolds through State-Occupancy Matching
par: Fraschini, Andrea, et autres
Publié: (2026)

Towards Principled Unsupervised Multi-Agent Reinforcement Learning
par: Zamboni, Riccardo, et autres
Publié: (2025)

How to Explore with Belief: State Entropy Maximization in POMDPs
par: Zamboni, Riccardo, et autres
Publié: (2024)

The Limits of Pure Exploration in POMDPs: When the Observation Entropy is Enough
par: Zamboni, Riccardo, et autres
Publié: (2024)

Enhancing Diversity in Parallel Agents: A Maximum State Entropy Exploration Story
par: De Paola, Vincenzo, et autres
Publié: (2025)

K-Myriad: Jump-starting reinforcement learning with unsupervised parallel agents
par: De Paola, Vincenzo, et autres
Publié: (2026)

Statistical Analysis of Policy Space Compression Problem
par: Molaei, Majid, et autres
Publié: (2024)

Projection by Convolution: Optimal Sample Complexity for Reinforcement Learning in Continuous-Space MDPs
par: Maran, Davide, et autres
Publié: (2024)

How Log-Barrier Helps Exploration in Policy Optimization
par: Cesani, Leonardo, et autres
Publié: (2026)

Scalable Multi-Agent Offline Reinforcement Learning and the Role of Information
par: Zamboni, Riccardo, et autres
Publié: (2025)

Inverse Reinforcement Learning with Sub-optimal Experts
par: Poiani, Riccardo, et autres
Publié: (2024)

Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning
par: Mutti, Mirco, et autres
Publié: (2023)

Building surrogate models using trajectories of agents trained by Reinforcement Learning
par: Cestero, Julen, et autres
Publié: (2025)

A Theoretical Framework for Partially Observed Reward-States in RLHF
par: Kausik, Chinmaya, et autres
Publié: (2024)

Finite Sample Bounds for Non-Parametric Regression: Optimal Sample Efficiency and Space Complexity
par: Maran, Davide, et autres
Publié: (2024)

Limitations of Physics-Informed Neural Networks: a Study on Smart Grid Surrogation
par: Cestero, Julen, et autres
Publié: (2025)

Optimizing Energy Management of Smart Grid using Reinforcement Learning aided by Surrogate models built using Physics-informed Neural Networks
par: Cestero, Julen, et autres
Publié: (2025)

Online Market Making and the Value of Observing the Order Book
par: Maran, Davide, et autres
Publié: (2026)

Parameterized Projected Bellman Operator
par: Vincent, Théo, et autres
Publié: (2023)

Complexity-Regularized Proximal Policy Optimization
par: Serfilippi, Luca, et autres
Publié: (2025)

Efficient On-Policy Reinforcement Learning via Exploration of Sparse Parameter Space
par: Zhang, Xinyu, et autres
Publié: (2025)

Tree Search in DAG Space with Model-based Reinforcement Learning for Causal Discovery
par: Darvariu, Victor-Alexandru, et autres
Publié: (2023)

Training Foundation Models as Data Compression: On Information, Model Weights and Copyright Law
par: Franceschelli, Giorgio, et autres
Publié: (2024)

From Entanglement to Alignment: Representation Space Decomposition for Unsupervised Time Series Domain Adaptation
par: Cai, Rongyao, et autres
Publié: (2025)

Solution Space Topology Guides CMTS Search
par: Mannucci, Mirco A.
Publié: (2025)

Learning in Markov Decision Processes with Exogenous Dynamics
par: Maran, Davide, et autres
Publié: (2026)

Spectral Geometry for Deep Learning: Compression and Hallucination Detection via Random Matrix Theory
par: Ettori, Davide
Publié: (2026)

Gym4ReaL: A Suite for Benchmarking Real-World Reinforcement Learning
par: Salaorni, Davide, et autres
Publié: (2025)

Discovering Behavioral Modes in Deep Reinforcement Learning Policies Using Trajectory Clustering in Latent Space
par: Remman, Sindre Benjamin, et autres
Publié: (2024)

Exploring Token-Space Manipulation in Latent Audio Tokenizers
par: Paissan, Francesco, et autres
Publié: (2026)

Truncating Trajectories in Monte Carlo Policy Evaluation: an Adaptive Approach
par: Poiani, Riccardo, et autres
Publié: (2024)

Diversifying Policy Behaviors with Extrinsic Behavioral Curiosity
par: Wan, Zhenglin, et autres
Publié: (2024)

Exploration Behavior of Untrained Policies
par: Adamczyk, Jacob
Publié: (2025)

Heterogeneous Knowledge for Augmented Modular Reinforcement Learning
par: Wolf, Lorenz, et autres
Publié: (2023)

Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challenges
par: Franceschelli, Giorgio, et autres
Publié: (2023)

Do Agents Dream of Electric Sheep?: Improving Generalization in Reinforcement Learning through Generative Learning
par: Franceschelli, Giorgio, et autres
Publié: (2024)

Symmetry in Neural Network Parameter Spaces
par: Zhao, Bo, et autres
Publié: (2025)

GradientSpace: Unsupervised Data Clustering for Improved Instruction Tuning
par: Sridharan, Shrihari, et autres
Publié: (2025)

Adaptive Compression of the Latent Space in Variational Autoencoders
par: Sejnova, Gabriela, et autres
Publié: (2023)

Learning to Explore with Parameter-Space Noise: A Deep Dive into Parameter-Space Noise for Reinforcement Learning with Verifiable Rewards
par: Bai, Bizhe, et autres
Publié: (2026)