Unsupervised Reinforcement Learning

Benchmarks archive 2025-07-28

No benchmark for this task in the archive.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

2 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Most implemented papers archive 2025-07-28

29 shown of 29 papers with code (57 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Exploration by Random Network Distillation
  30 Oct 2018 22 repositories listed Syntology ran 26 of 43 samples · 17 unverified · 15 pointer-only (licence)
  In particular we establish state of the art performance on Montezuma's Revenge, a game famously difficult for deep reinforcement learning methods.
• Curiosity-driven Exploration by Self-supervised Prediction
  15 May 2017 13 repositories listed Syntology ran 16 of 32 samples · 16 unverified · 14 pointer-only (licence)
  In many real-world scenarios, rewards extrinsic to the agent are extremely sparse, or absent altogether.
• Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning
  20 Jul 2021 8 repositories listed Syntology ran 5 of 5 samples · 0 unverified
  We present DrQ-v2, a model-free reinforcement learning (RL) algorithm for visual continuous control.
• Diversity is All You Need: Learning Skills without a Reward Function
  16 Feb 2018 4 repositories listed Syntology ran 5 of 11 samples · 6 unverified
  On a variety of simulated robotic tasks, we show that this simple objective results in the unsupervised emergence of diverse skills, such as walking and jumping.
• Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation Models
  15 Apr 2025 2 repositories listed Syntology ran 16 of 31 samples · 15 unverified · 31 pointer-only (licence)
  Unsupervised reinforcement learning (RL) aims at pre-training agents that can solve a wide range of downstream tasks in complex environments.
• Unsupervised Reinforcement Learning in Multiple Environments
  16 Dec 2021 2 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  Along this line, we address the problem of unsupervised reinforcement learning in a class of multiple environments, in which the policy is pre-trained with interactions from the whole class, and then fine-tuned for…
• Emergent Real-World Robotic Skills via Unsupervised Off-Policy Reinforcement Learning
  27 Apr 2020 2 repositories listed Syntology ran 2 of 3 samples · 1 unverified
  Can we instead develop efficient reinforcement learning methods that acquire diverse skills without any reward function, and then repurpose these skills for downstream tasks?
• Self-Supervised Exploration via Disagreement
  10 Jun 2019 2 repositories listed
  In this paper, we propose a formulation for exploration inspired by the work in active learning literature.
• Surprise-Adaptive Intrinsic Motivation for Unsupervised Reinforcement Learning
  27 May 2024 1 repository listed
  In an effort to find a single entropy-based method that will encourage emergent behaviors in any environment, we propose an agent that can adapt its objective online, depending on the entropy conditions by framing the…
• M2CURL: Sample-Efficient Multimodal Reinforcement Learning via Self-Supervised Representation Learning for Robotic Manipulation
  30 Jan 2024 1 repository listed
  One of the most critical aspects of multimodal Reinforcement Learning (RL) is the effective integration of different observation modalities.
• METRA: Scalable Unsupervised RL with Metric-Aware Abstraction
  13 Oct 2023 1 repository listed Syntology ran 0 of 1 samples · 1 unverified
  Through our experiments in five locomotion and manipulation environments, we demonstrate that METRA can discover a variety of useful behaviors even in complex, pixel-based environments, being the first unsupervised RL…
• ComSD: Balancing Behavioral Quality and Diversity in Unsupervised Skill Discovery
  29 Sep 2023 1 repository listed
  It contains a particle-based exploration reward to make agents access far-reaching states for exploratory skill acquisition, and a novel contrastive diversity reward to promote the discriminability between different…
• CRC-RL: A Novel Visual Feature Representation Architecture for Unsupervised Reinforcement Learning
  31 Jan 2023 1 repository listed
  This paper addresses the problem of visual feature representation learning with an aim to improve the performance of end-to-end reinforcement learning (RL) models.
• Choreographer: Learning and Adapting Skills in Imagination
  23 Nov 2022 1 repository listed Syntology ran 1 of 2 samples · 1 unverified · 1 pointer-only (licence)
  Unsupervised skill learning aims to learn a rich repertoire of behaviors without external supervision, providing artificial agents with the ability to control and influence the environment.
• Skill-Based Reinforcement Learning with Intrinsic Reward Matching
  14 Oct 2022 1 repository listed
  While unsupervised skill discovery has shown promise in autonomously acquiring behavioral primitives, there is still a large methodological disconnect between task-agnostic skill pretraining and downstream, task-aware…
• A Mixture of Surprises for Unsupervised Reinforcement Learning
  13 Oct 2022 1 repository listed Syntology ran 1 of 12 samples · 11 unverified
  However, both strategies rely on a strong assumption: the entropy of the environment's dynamics is either high or low.
• Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels
  24 Sep 2022 1 repository listed Syntology ran 17 of 24 samples · 7 unverified
  In this work, we study the URLB and propose a new method to solve it, using unsupervised model-based RL, for pre-training the agent, and a task-aware fine-tuning strategy combined with a new proposed hybrid planner,…
• Impact Makes a Sound and Sound Makes an Impact: Sound Guides Representations and Explorations
  4 Aug 2022 1 repository listed
  Sound is one of the most informative and abundant modalities in the real world while being robust to sense without contacts by small and cheap sensors that can be placed on mobile devices.
• ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters
  4 May 2022 1 repository listed Syntology ran 0 of 7 samples · 7 unverified
  By leveraging a massively parallel GPU-based simulator, we are able to train skill embeddings using over a decade of simulated experiences, enabling our model to learn a rich and versatile repertoire of skills.
• CIC: Contrastive Intrinsic Control for Unsupervised Skill Discovery
  1 Feb 2022 1 repository listed Syntology ran 1 of 2 samples · 1 unverified · 2 pointer-only (licence)
  We introduce Contrastive Intrinsic Control (CIC), an algorithm for unsupervised skill discovery that maximizes the mutual information between state-transitions and latent skill vectors.
• URLB: Unsupervised Reinforcement Learning Benchmark
  28 Oct 2021 1 repository listed Syntology ran 0 of 1 samples · 1 unverified · 1 pointer-only (licence)
  Deep Reinforcement Learning (RL) has emerged as a powerful paradigm to solve a range of complex yet specific control tasks.
• The Information Geometry of Unsupervised Reinforcement Learning
  6 Oct 2021 1 repository listed
  In this work, we show that unsupervised skill discovery algorithms based on mutual information maximization do not learn skills that are optimal for every possible reward function.
• Unsupervised multi-latent space reinforcement learning framework for video summarization in ultrasound imaging
  3 Sep 2021 1 repository listed
  Using an attention ensemble of encoders, the high dimensional image is projected into a low dimensional latent space in terms of: a) reduced distance with a normal or abnormal class (classifier encoder), b) following a…
• Explore and Control with Adversarial Surprise
  12 Jul 2021 1 repository listed Syntology ran 1 of 2 samples · 1 unverified · 2 pointer-only (licence)
  Unsupervised reinforcement learning (RL) studies how to leverage environment statistics to learn useful behaviors without the cost of reward engineering.
• Behavior From the Void: Unsupervised Active Pre-Training
  8 Mar 2021 1 repository listed Syntology ran 1 of 6 samples · 5 unverified
  We introduce a new unsupervised pre-training method for reinforcement learning called APT, which stands for Active Pre-Training.
• Reinforcement Learning with Prototypical Representations
  22 Feb 2021 1 repository listed
  Unfortunately, in RL, representation learning is confounded with the exploratory experience of the agent -- learning a useful representation requires diverse data, while effective exploration is only possible with…
• SMiRL: Surprise Minimizing Reinforcement Learning in Unstable Environments
  11 Dec 2019 1 repository listed
  Every living organism struggles against disruptive environmental forces to carve out and maintain an orderly niche.
• Efficient Exploration via State Marginal Matching
  12 Jun 2019 1 repository listed
  The SMM objective can be viewed as a two-player, zero-sum game between a state density model and a parametric policy, an idea that we use to build an algorithm for optimizing the SMM objective.
• Variational Intrinsic Control
  22 Nov 2016 1 repository listed
  In this paper we introduce a new unsupervised reinforcement learning method for discovering the set of intrinsic options available to an agent.

Syntology lines on 16 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.