Unsupervised Reinforcement Learning
26 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
Exploration by Random Network Distillation
openai/random-network-distillation
•
•
ICLR 2019
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
pathak22/noreward-rl
•
•
ICML 2017
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
facebookresearch/drqv2
•
•
ICLR 2022
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
alirezakazemipour/DIAYN-PyTorch
•
•
ICLR 2019
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.
Self-Supervised Exploration via Disagreement
pathak22/exploration-by-disagreement
•
•
In this paper, we propose a formulation for exploration inspired by the work in active learning literature.
Emergent Real-World Robotic Skills via Unsupervised Off-Policy Reinforcement Learning
Can we instead develop efficient reinforcement learning methods that acquire diverse skills without any reward function, and then repurpose these skills for downstream tasks?
Unsupervised Reinforcement Learning in Multiple Environments
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 several tasks in any environment of the class.
Variational Intrinsic Control
jbinas/gym-mnist
•
•
In this paper we introduce a new unsupervised reinforcement learning method for discovering the set of intrinsic options available to an agent.
Efficient Exploration via State Marginal Matching
RLAgent/state-marginal-matching
•
•
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.
SMiRL: Surprise Minimizing Reinforcement Learning in Unstable Environments
chenziku/train-procgen
•
•
ICLR 2021
Every living organism struggles against disruptive environmental forces to carve out and maintain an orderly niche.
