Cover Image

From Parameters to Behaviors: Unsupervised Compression of the Policy Space

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tenedini, Davide, Zamboni, Riccardo, Mutti, Mirco, Restelli, Marcello
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Unsupervised Behavioral Compression: Learning Low-Dimensional Policy Manifolds through State-Occupancy Matching
by: Fraschini, Andrea, et al.
Published: (2026)

Towards Principled Unsupervised Multi-Agent Reinforcement Learning
by: Zamboni, Riccardo, et al.
Published: (2025)

How to Explore with Belief: State Entropy Maximization in POMDPs
by: Zamboni, Riccardo, et al.
Published: (2024)

The Limits of Pure Exploration in POMDPs: When the Observation Entropy is Enough
by: Zamboni, Riccardo, et al.
Published: (2024)

Enhancing Diversity in Parallel Agents: A Maximum State Entropy Exploration Story
by: De Paola, Vincenzo, et al.
Published: (2025)

K-Myriad: Jump-starting reinforcement learning with unsupervised parallel agents
by: De Paola, Vincenzo, et al.
Published: (2026)

Statistical Analysis of Policy Space Compression Problem
by: Molaei, Majid, et al.
Published: (2024)

Projection by Convolution: Optimal Sample Complexity for Reinforcement Learning in Continuous-Space MDPs
by: Maran, Davide, et al.
Published: (2024)

How Log-Barrier Helps Exploration in Policy Optimization
by: Cesani, Leonardo, et al.
Published: (2026)

Scalable Multi-Agent Offline Reinforcement Learning and the Role of Information
by: Zamboni, Riccardo, et al.
Published: (2025)

Inverse Reinforcement Learning with Sub-optimal Experts
by: Poiani, Riccardo, et al.
Published: (2024)

Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning
by: Mutti, Mirco, et al.
Published: (2023)

Building surrogate models using trajectories of agents trained by Reinforcement Learning
by: Cestero, Julen, et al.
Published: (2025)

A Theoretical Framework for Partially Observed Reward-States in RLHF
by: Kausik, Chinmaya, et al.
Published: (2024)

Finite Sample Bounds for Non-Parametric Regression: Optimal Sample Efficiency and Space Complexity
by: Maran, Davide, et al.
Published: (2024)

Limitations of Physics-Informed Neural Networks: a Study on Smart Grid Surrogation
by: Cestero, Julen, et al.
Published: (2025)

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

Online Market Making and the Value of Observing the Order Book
by: Maran, Davide, et al.
Published: (2026)

Parameterized Projected Bellman Operator
by: Vincent, Théo, et al.
Published: (2023)

Complexity-Regularized Proximal Policy Optimization
by: Serfilippi, Luca, et al.
Published: (2025)

Efficient On-Policy Reinforcement Learning via Exploration of Sparse Parameter Space
by: Zhang, Xinyu, et al.
Published: (2025)

Tree Search in DAG Space with Model-based Reinforcement Learning for Causal Discovery
by: Darvariu, Victor-Alexandru, et al.
Published: (2023)

Training Foundation Models as Data Compression: On Information, Model Weights and Copyright Law
by: Franceschelli, Giorgio, et al.
Published: (2024)

From Entanglement to Alignment: Representation Space Decomposition for Unsupervised Time Series Domain Adaptation
by: Cai, Rongyao, et al.
Published: (2025)

Solution Space Topology Guides CMTS Search
by: Mannucci, Mirco A.
Published: (2025)

Learning in Markov Decision Processes with Exogenous Dynamics
by: Maran, Davide, et al.
Published: (2026)

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

Gym4ReaL: A Suite for Benchmarking Real-World Reinforcement Learning
by: Salaorni, Davide, et al.
Published: (2025)

Discovering Behavioral Modes in Deep Reinforcement Learning Policies Using Trajectory Clustering in Latent Space
by: Remman, Sindre Benjamin, et al.
Published: (2024)

Exploring Token-Space Manipulation in Latent Audio Tokenizers
by: Paissan, Francesco, et al.
Published: (2026)

Truncating Trajectories in Monte Carlo Policy Evaluation: an Adaptive Approach
by: Poiani, Riccardo, et al.
Published: (2024)

Diversifying Policy Behaviors with Extrinsic Behavioral Curiosity
by: Wan, Zhenglin, et al.
Published: (2024)

Exploration Behavior of Untrained Policies
by: Adamczyk, Jacob
Published: (2025)

Heterogeneous Knowledge for Augmented Modular Reinforcement Learning
by: Wolf, Lorenz, et al.
Published: (2023)

Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challenges
by: Franceschelli, Giorgio, et al.
Published: (2023)

Do Agents Dream of Electric Sheep?: Improving Generalization in Reinforcement Learning through Generative Learning
by: Franceschelli, Giorgio, et al.
Published: (2024)

Symmetry in Neural Network Parameter Spaces
by: Zhao, Bo, et al.
Published: (2025)

GradientSpace: Unsupervised Data Clustering for Improved Instruction Tuning
by: Sridharan, Shrihari, et al.
Published: (2025)

Adaptive Compression of the Latent Space in Variational Autoencoders
by: Sejnova, Gabriela, et al.
Published: (2023)

Learning to Explore with Parameter-Space Noise: A Deep Dive into Parameter-Space Noise for Reinforcement Learning with Verifiable Rewards
by: Bai, Bizhe, et al.
Published: (2026)