Skew-Fit: State-Covering Self-Supervised Reinforcement Learning
March 08, 2019 ยท Declared Dead ยท ๐ International Conference on Machine Learning
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Vitchyr H. Pong, Murtaza Dalal, Steven Lin, Ashvin Nair, Shikhar Bahl, Sergey Levine
arXiv ID
1903.03698
Category
cs.LG: Machine Learning
Cross-listed
cs.AI,
cs.RO,
stat.ML
Citations
299
Venue
International Conference on Machine Learning
Last Checked
3 months ago
Abstract
Autonomous agents that must exhibit flexible and broad capabilities will need to be equipped with large repertoires of skills. Defining each skill with a manually-designed reward function limits this repertoire and imposes a manual engineering burden. Self-supervised agents that set their own goals can automate this process, but designing appropriate goal setting objectives can be difficult, and often involves heuristic design decisions. In this paper, we propose a formal exploration objective for goal-reaching policies that maximizes state coverage. We show that this objective is equivalent to maximizing goal reaching performance together with the entropy of the goal distribution, where goals correspond to full state observations. To instantiate this principle, we present an algorithm called Skew-Fit for learning a maximum-entropy goal distributions. We prove that, under regularity conditions, Skew-Fit converges to a uniform distribution over the set of valid states, even when we do not know this set beforehand. Our experiments show that combining Skew-Fit for learning goal distributions with existing goal-reaching methods outperforms a variety of prior methods on open-sourced visual goal-reaching tasks. Moreover, we demonstrate that Skew-Fit enables a real-world robot to learn to open a door, entirely from scratch, from pixels, and without any manually-designed reward function.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ Machine Learning
R.I.P.
๐ป
Ghosted
R.I.P.
๐ป
Ghosted
XGBoost: A Scalable Tree Boosting System
R.I.P.
๐ป
Ghosted
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
R.I.P.
๐ป
Ghosted
Semi-Supervised Classification with Graph Convolutional Networks
R.I.P.
๐ป
Ghosted
Proximal Policy Optimization Algorithms
R.I.P.
๐ป
Ghosted
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Died the same way โ ๐ป Ghosted
R.I.P.
๐ป
Ghosted
Language Models are Few-Shot Learners
R.I.P.
๐ป
Ghosted
You Only Look Once: Unified, Real-Time Object Detection
R.I.P.
๐ป
Ghosted
A Unified Approach to Interpreting Model Predictions
R.I.P.
๐ป
Ghosted