An Intrinsically-Motivated Approach for Learning Highly Exploring and
Fast Mixing Policies

v1v2 (latest)

An Intrinsically-Motivated Approach for Learning Highly Exploring and Fast Mixing Policies

10 July 2019

Marcello Restelli

ArXiv (abs)PDF HTML

Papers citing "An Intrinsically-Motivated Approach for Learning Highly Exploring and Fast Mixing Policies"

6 / 6 papers shown

Title
Enhancing Diversity in Parallel Agents: A Maximum State Entropy Exploration Story Vincenzo De Paola Riccardo Zamboni Mirco Mutti Marcello Restelli 116 0 0 02 May 2025
The Importance of Non-Markovianity in Maximum State Entropy Exploration Mirco Mutti Ric De Santi Marcello Restelli 87 33 0 07 Feb 2022
Challenging Common Assumptions in Convex Reinforcement Learning Mirco Mutti Ric De Santi Piersilvio De Bartolomeis Marcello Restelli OffRL 78 23 0 03 Feb 2022
Action Redundancy in Reinforcement Learning Nir Baram Guy Tennenholtz Shie Mannor 74 8 0 22 Feb 2021
Geometric Entropic Exploration Z. Guo M. G. Azar Alaa Saade S. Thakoor Bilal Piot Bernardo Avila-Pires Michal Valko Thomas Mesnard Tor Lattimore Rémi Munos 89 32 0 06 Jan 2021
Task-Agnostic Exploration via Policy Gradient of a Non-Parametric State Entropy Estimate Mirco Mutti Lorenzo Pratissoli Marcello Restelli 73 19 0 09 Jul 2020