# Weakly-Supervised Reinforcement Learning for Controllable Behavior

arXiv: https://arxiv.org/abs/2004.02860 · HTML: https://mlsanity.com/paper/2004.02860/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Apr 2020.

## Built on by (most cited first, 17 of 17)

- [Goal-Conditioned Reinforcement Learning: Problems and Solutions](https://mlsanity.com/paper/2201.08299/) (2022)
- [Spectral Decomposition Representation for Reinforcement Learning](https://mlsanity.com/paper/2208.09515/) (2022)
- [Learning Domain Invariant Representations in Goal-conditioned Block MDPs](https://mlsanity.com/paper/2110.14248/) (2021)
- [Weakly Supervised Correspondence Learning](https://mlsanity.com/paper/2203.00904/) (2022)
- [Relative Behavioral Attributes: Filling the Gap between Symbolic Goal Specification and Reward Learning from Human Preferences](https://mlsanity.com/paper/2210.15906/) (2022)
- [Distributional Reward Estimation for Effective Multi-Agent Deep Reinforcement Learning](https://mlsanity.com/paper/2210.07636/) (2022)
- [Learning to Play Atari in a World of Tokens](https://mlsanity.com/paper/2406.01361/) (2024)
- [Learning State Representations via Retracing in Reinforcement Learning](https://mlsanity.com/paper/2111.12600/) (2021)
- [Toddler-Guidance Learning: Impacts of Critical Period on Multimodal AI Agents](https://mlsanity.com/paper/2201.04990/) (2022)
- [Sampling Through the Lens of Sequential Decision Making](https://mlsanity.com/paper/2208.08056/) (2022)
- [A Survey on Explainable Reinforcement Learning: Concepts, Algorithms, Challenges](https://mlsanity.com/paper/2211.06665/) (2022)
- [Weakly Supervised Reinforcement Learning for Autonomous Highway Driving via Virtual Safety Cages](https://mlsanity.com/paper/2103.09726/) (2021)
- [Learning user-defined sub-goals using memory editing in reinforcement learning](https://mlsanity.com/paper/2205.00399/) (2022)
- [An MRP Formulation for Supervised Learning: Generalized Temporal Difference Learning Models](https://mlsanity.com/paper/2404.15518/) (2024)
- [Open Problem: Active Representation Learning](https://mlsanity.com/paper/2406.03845/) (2024)
- [A Fully Controllable Agent in the Path Planning using Goal-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2205.09967/) (2022)
- [Goal-Conditioned Terminal Value Estimation for Real-time and Multi-task Model Predictive Control](https://mlsanity.com/paper/2410.04929/) (2024)

## Abstract (arXiv)

Reinforcement learning (RL) is a powerful framework for learning to take actions to solve tasks. However, in many settings, an agent must winnow down the inconceivably large space of all possible tasks to the single task that it is currently being asked to solve. Can we instead constrain the space of tasks to those that are semantically meaningful? In this work, we introduce a framework for using weak supervision to automatically disentangle this semantically meaningful subspace of tasks from the enormous space of nonsensical "chaff" tasks. We show that this learned subspace enables efficient exploration and provides a representation that captures distance between states. On a variety of challenging, vision-based continuous control problems, our approach leads to substantial performance gains, particularly as the complexity of the environment grows.