Friday, March 25, 2022
HomeArtificial IntelligenceThe Unsupervised Reinforcement Studying Benchmark – The Berkeley Synthetic Intelligence Analysis Weblog

The Unsupervised Reinforcement Studying Benchmark – The Berkeley Synthetic Intelligence Analysis Weblog


Reinforcement Studying (RL) is a strong paradigm for fixing many issues of curiosity in AI, akin to controlling autonomous automobiles, digital assistants, and useful resource allocation to call just a few. We’ve seen during the last 5 years that, when supplied with an extrinsic reward operate, RL brokers can grasp very complicated duties like taking part in Go, Starcraft, and dextrous robotic manipulation. Whereas large-scale RL brokers can obtain beautiful outcomes, even the most effective RL brokers in the present day are slim. Most RL algorithms in the present day can solely clear up the one process they have been skilled on and don’t exhibit cross-task or cross-domain generalization capabilities.

A side-effect of the narrowness of in the present day’s RL methods is that in the present day’s RL brokers are additionally very information inefficient. If we have been to coach AlphaGo-like brokers on many duties every agent would probably require billions of coaching steps as a result of in the present day’s RL brokers don’t have the capabilities to reuse prior data to unravel new duties extra effectively. RL as we all know it’s supervised – brokers overfit to a selected extrinsic reward which limits their potential to generalize.



So far, probably the most promising path towards generalist AI methods in language and imaginative and prescient has been via unsupervised pre-training. Masked informal and bi-directional transformers have emerged as scalable strategies for pre-training language fashions which have proven unprecedented generalization capabilities. Siamese architectures and extra lately masked auto-encoders have additionally develop into state-of-the-art strategies for attaining quick downstream process adaptation in imaginative and prescient.

If we imagine that pre-training is a strong strategy in direction of creating generalist AI brokers, then it’s pure to ask whether or not there exist self-supervised targets that may permit us to pre-train RL brokers. In contrast to imaginative and prescient and language fashions which act on static information, RL algorithms actively affect their very own information distribution. Like in imaginative and prescient and language, illustration studying is a vital side for RL as effectively however the unsupervised drawback that’s distinctive to RL is how brokers can themselves generate fascinating and various information trough self-supervised targets. That is the unsupervised RL drawback – how will we be taught helpful behaviors with out supervision after which adapt them to unravel downstream duties shortly?

Unsupervised RL is similar to supervised RL. Each assume that the underlying atmosphere is described by a Markov Determination Course of (MDP) or a Partially Noticed MDP, and each purpose to maximise rewards. The principle distinction is that supervised RL assumes that supervision is supplied by the atmosphere via an extrinsic reward whereas unsupervised RL defines an intrinsic reward via a self-supervised process. Like supervision in NLP and imaginative and prescient, supervised rewards are both engineered or supplied as labels by human operators that are onerous to scale and restrict the generalization of RL algorithms to particular duties.


On the Robotic Studying Lab (RLL), we’ve been taking steps towards making unsupervised RL a believable strategy towards creating RL brokers able to generalization. To this finish, we developed and launched a benchmark for unsupervised RL with open-sourced PyTorch code for 8 main or standard baselines.

The Unsupervised Reinforcement Studying Benchmark (URLB)

Whereas quite a lot of unsupervised RL algorithms have been proposed over the previous couple of years, it has been unimaginable to check them pretty attributable to variations in analysis, environments, and optimization. For that reason, we constructed URLB which offers standardized analysis procedures, domains, downstream duties, and optimization for unsupervised RL algorithms

URLB splits coaching into two phases – a protracted unsupervised pre-training part adopted by a brief supervised fine-tuning part. The preliminary launch consists of three domains with 4 duties every for a complete of twelve downstream duties for analysis.


Most unsupervised RL algorithms recognized up to now will be categorized into three classes – knowledge-based, data-based, and competence-based. Information-based strategies maximize the prediction error or uncertainty of a predictive mannequin (e.g. Curiosity, Disagreement, RND), data-based strategies maximize the range of noticed information (e.g. APT, ProtoRL), competence-based strategies maximize the mutual info between states and a few latent vector sometimes called the “ability” or “process” vector (e.g. DIAYN, SMM, APS).

Beforehand these algorithms have been applied utilizing completely different optimization algorithms (Rainbow DQN, DDPG, PPO, SAC, and so on). Because of this, unsupervised RL algorithms have been onerous to check. In our implementations we standardize the optimization algorithm such that the one distinction between varied baselines is the self-supervised goal.


We applied and launched code for eight main algorithms supporting each state and pixel-based observations on domains based mostly on the DeepMind Management Suite.


By standardizing domains, analysis, and optimization throughout all applied baselines in URLB, the result’s a primary direct and truthful comparability between these three various kinds of algorithms.


Above, we present combination statistics of fine-tuning runs throughout all 12 downstream duties with 10 seeds every after pre-training on the goal area for 2M steps. We discover that presently data-based strategies (APT, ProtoRL) and RND are the main approaches on URLB.

We’ve additionally recognized various promising instructions for future analysis based mostly on benchmarking current strategies. For instance, competence-based exploration as an entire underperforms information and knowledge-based exploration. Understanding why that is the case is an fascinating line for additional analysis. For added insights and instructions for future analysis in unsupervised RL, we refer the reader to the URLB paper.

Unsupervised RL is a promising path towards creating generalist RL brokers. We’ve launched a benchmark (URLB) for evaluating the efficiency of such brokers. We’ve open-sourced code for each URLB and hope this allows different researchers to shortly prototype and consider unsupervised RL algorithms.

Paper: URLB: Unsupervised Reinforcement Studying Benchmark
Michael Laskin*, Denis Yarats*, Hao Liu, Kimin Lee, Albert Zhan, Kevin Lu, Catherine Cang, Lerrel Pinto, Pieter Abbeel, NeurIPS, 2021, these authors contributed equally




Please enter your comment!
Please enter your name here

Most Popular

Recent Comments