No article text was recorded for this version.
mutual information maximization (mutual information-based skill discovery)
Version 1 of 191 papers123 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Robustifying a Policy in Multi-Agent RL with Diverse Cooperative Behaviors and Adversarial Style Sampling for Assistive Tasks
- Blog: The Emergence of Individuality
- Blog: Discovering diverse solutions in deep reinforcement learning by maximizing state-action-based mutual information
- Blog: Diversity is All You Need: Learning Skills without a Reward Function
- Blog: An information-theoretic perspective on intrinsic motivation in reinforcement learning: a survey
- Blog: Self-Improving World Modelling with Latent Actions
- Blog: Celebrating Diversity in Shared Multi-Agent Reinforcement Learning
- Blog: Emergent Real-World Robotic Skills via Unsupervised Off-Policy Reinforcement Learning
- Blog: MAVEN: Multi-Agent Variational Exploration
- Blog: The Emergence of Individuality
- Blog: Continuously Discovering Novel Strategies via Reward-Switching Policy Optimization
- Blog: Stochastic Neural Networks for Hierarchical Reinforcement Learning
- Blog: Discovering Multiple Solutions from a Single Task in Offline Reinforcement Learning
- Blog: An information-theoretic perspective on intrinsic motivation in reinforcement learning
- Blog: Discovering Diverse Solutions in Deep Reinforcement Learning by Maximizing State-Action-Based Mutual Information
- Blog: Skill Transfer via Partially Amortized Hierarchical Planning
- Blog: Dynamics-Aware Unsupervised Discovery of Skills
- Blog: Learning to Coordinate Manipulation Skills via Skill Behavior Diversification
- Blog: Reference Grounded Skill Discovery
- Blog: Discovering Diverse Solutions in Deep Reinforcement Learning
- Blog: Behavioral Mode Discovery for Fine-tuning Multimodal Generative Policies
- Blog: ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters
- Blog: Learning Fairness in Multi-Agent Systems
- Blog: Fast Task Inference with Variational Intrinsic Successor Features
- Blog: Direct then Diffuse: Incremental Unsupervised Skill Discovery for State Covering and Goal Reaching
- Blog: APS: Active Pretraining with Successor Features
- Blog: Heterogeneous Skill Learning for Multi-agent Tasks
- Blog: Improving the Generalization of Unseen Crowd Behaviors for Reinforcement Learning based Local Motion Planners
- Blog: SOAC: The Soft Option Actor-Critic Architecture
- Blog: URLB: Unsupervised Reinforcement Learning Benchmark
- Blog: InfoSTGCAN: An Information-Maximizing Spatial-Temporal Graph Convolutional Attention Network for Heterogeneous Human Trajectory Prediction
- Blog: Learning Temporally Extended Skills in Continuous Domains as Symbolic Actions for Planning
- Blog: CIC: Contrastive Intrinsic Control for Unsupervised Skill Discovery
- Blog: Any-Play: An Intrinsic Augmentation for Zero-Shot Coordination
- Blog: Hierarchical Empowerment: Towards Tractable Empowerment-Based Skill-Learning
- Blog: Multi-Modal Imitation Learning from Unstructured Demonstrations using Generative Adversarial Nets
- Blog: Obstacle-Aware Quadrupedal Locomotion With Resilient Multi-Modal Reinforcement Learning
- Blog: Diversity is All You Need: Learning Skills without a Reward Function
- Blog: Evolution of a Complex Predator-Prey Ecosystem on Large-scale Multi-Agent Deep Reinforcement Learning
- Blog: The impact of intrinsic rewards on exploration in Reinforcement Learning
- Blog: One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL
- Blog: SMAUG: A Sliding Multidimensional Task Window-Based MARL Framework for Adaptive Real-Time Subtask Recognition
- Blog: Variational Intrinsic Control
- Blog: A Mixture of Surprises for Unsupervised Reinforcement Learning
- Blog: Learning Distinguishable Trajectory Representation with Contrastive Loss
- Blog: Skill-aware Mutual Information Optimisation for Zero-shot Generalisation in Reinforcement Learning
- Blog: DGPO: Discovering Multiple Strategies with Diversity-Guided Policy Optimization
- Blog: Latent Skill Planning for Exploration and Transfer
- Blog: Versatile Skill Control via Self-supervised Adversarial Imitation of Unlabeled Mixed Motions
- Blog: Hierarchical Reinforcement Learning via Advantage-Weighted Information Maximization
- Blog: InfoGAIL: Interpretable Imitation Learning from Visual Demonstrations
- Blog: ADMN: Agent-Driven Modular Network for Dynamic Parameter Sharing in Cooperative Multi-Agent Reinforcement Learning
- Blog: Diverse Offline Imitation via Fenchel Duality
- Blog: Leveraging Approximate Symbolic Models for Reinforcement Learning via Skill Diversity
- Blog: Emergent Real-World Robotic Skills via Unsupervised Off-Policy Reinforcement Learning
- Blog: Multi-task Hierarchical Adversarial Inverse Reinforcement Learning
- Blog: Hierarchical Multi-Agent Skill Discovery
- Blog: Discovering Multiple Solutions from a Single Task in Offline Reinforcement Learning
- Blog: S-EPOA: Overcoming the Indistinguishability of Segments with Skill-Driven Preference-Based Reinforcement Learning
- Blog: Offline Reinforcement Learning with Mixture of Deterministic Policies
Showing 60 of 91 papers.
History & citation
Current · Permanent link
- Unsupervised Skill Discovery through Mutual Information merged into this direction (54% overlap)
- Latent Skill Discovery through Mutual Information Maximization merged into this direction (80% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_mutual_information_maximization_mutual_i_04feb62f,
title = {mutual information maximization (mutual information-based skill discovery)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/mutual-information-maximization-mutual-information-based-skill-discovery/rdr_04feb62f970047559c033ccce13ebd53},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_mutual_information_maximization_mutual_i_04feb62f_v1,
title = {mutual information maximization (mutual information-based skill discovery)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/mutual-information-maximization-mutual-information-based-skill-discovery/rdr_04feb62f970047559c033ccce13ebd53/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}