Unsupervised Reinforcement Learning
24 papers with code • 8 benchmarks • 2 datasets
Benchmarks
These leaderboards are used to track progress in Unsupervised Reinforcement Learning
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Unsupervised Reinforcement Learning models and implementations
URLB
bipedal-skills
Most implemented papers
Reinforcement Learning with Prototypical Representations
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 coherent representations.
Behavior From the Void: Unsupervised Active Pre-Training
rll-research/url_benchmark
•
•
NeurIPS 2021
We introduce a new unsupervised pre-training method for reinforcement learning called APT, which stands for Active Pre-Training.
Explore and Control with Adversarial Surprise
ArnaudFickinger/adversarial-surprise
•
•
ICML Workshop URL 2021
Unsupervised reinforcement learning (RL) studies how to leverage environment statistics to learn useful behaviors without the cost of reward engineering.
Unsupervised multi-latent space reinforcement learning framework for video summarization in ultrasound imaging
rpm1412/lus_video_summarization
•
•
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 topology of landmarks (segmentation encoder), and c) the distance or topology agnostic latent representation (convolutional autoencoders).
The Information Geometry of Unsupervised Reinforcement Learning
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.
URLB: Unsupervised Reinforcement Learning Benchmark
rll-research/url_benchmark
•
•
Deep Reinforcement Learning (RL) has emerged as a powerful paradigm to solve a range of complex yet specific control tasks.
CIC: Contrastive Intrinsic Control for Unsupervised Skill Discovery
rll-research/cic
•
•
We introduce Contrastive Intrinsic Control (CIC), an algorithm for unsupervised skill discovery that maximizes the mutual information between state-transitions and latent skill vectors.
Impact Makes a Sound and Sound Makes an Impact: Sound Guides Representations and Explorations
xf-zhao/iscm
•
•
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.
Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels
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, Dyna-MPC, to adapt the agent for downstream tasks.
A Mixture of Surprises for Unsupervised Reinforcement Learning
leaplabthu/moss
•
•
However, both strategies rely on a strong assumption: the entropy of the environment's dynamics is either high or low.
