# SAFER: Data-Efficient and Safe Reinforcement Learning via Skill Acquisition

arXiv: https://arxiv.org/abs/2202.04849 · HTML: https://mlsanity.com/paper/2202.04849/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 55 references that are in the map.
- First posted on arXiv 10 Feb 2022.

## Builds on (most cited first, 30 of 38)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016)
- [Constrained Policy Optimization](https://mlsanity.com/paper/1705.10528/) (2017)
- [Diversity is All You Need: Learning Skills without a Reward Function](https://mlsanity.com/paper/1802.06070/) (2018)
- [Data-Efficient Hierarchical Reinforcement Learning](https://mlsanity.com/paper/1805.08296/) (2018)
- [Do Deep Generative Models Know What They Don't Know?](https://mlsanity.com/paper/1810.09136/) (2018)
- [Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables](https://mlsanity.com/paper/1903.08254/) (2019)
- [Safe Model-based Reinforcement Learning with Stability Guarantees](https://mlsanity.com/paper/1705.08551/) (2017)
- [Dynamics-Aware Unsupervised Discovery of Skills](https://mlsanity.com/paper/1907.01657/) (2019)
- [A Lyapunov-based Approach to Safe Reinforcement Learning](https://mlsanity.com/paper/1805.07708/) (2018)
- [Safe Exploration in Continuous Action Spaces](https://mlsanity.com/paper/1801.08757/) (2018)
- [Advances in Variational Inference](https://mlsanity.com/paper/1711.05597/) (2017)
- [Accelerating Reinforcement Learning with Learned Skill Priors](https://mlsanity.com/paper/2010.11944/) (2020)
- [Why Normalizing Flows Fail to Detect Out-of-Distribution Data](https://mlsanity.com/paper/2006.08545/) (2020)
- [Projection-Based Constrained Policy Optimization](https://mlsanity.com/paper/2010.03152/) (2020)
- [Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones](https://mlsanity.com/paper/2010.15920/) (2020)
- [OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning](https://mlsanity.com/paper/2010.13611/) (2020)
- [Deep Reinforcement Learning in Large Discrete Action Spaces](https://mlsanity.com/paper/1512.07679/) (2015)
- [Parrot: Data-Driven Behavioral Priors for Reinforcement Learning](https://mlsanity.com/paper/2011.10024/) (2020)
- [Stochastic Neural Networks for Hierarchical Reinforcement Learning](https://mlsanity.com/paper/1704.03012/) (2017)
- [Learning to be Safe: Deep RL with a Safety Critic](https://mlsanity.com/paper/2010.14603/) (2020)
- [Safe Reinforcement Learning in Constrained Markov Decision Processes](https://mlsanity.com/paper/2008.06626/) (2020)
- [Conservative Safety Critics for Exploration](https://mlsanity.com/paper/2010.14497/) (2020)
- [Near-Optimal Representation Learning for Hierarchical Reinforcement Learning](https://mlsanity.com/paper/1810.01257/) (2018)
- [MCP: Learning Composable Hierarchical Control with Multiplicative Compositional Policies](https://mlsanity.com/paper/1905.09808/) (2019)
- [Demonstration-Guided Reinforcement Learning with Learned Skills](https://mlsanity.com/paper/2107.10253/) (2021)
- [Learning Action Representations for Reinforcement Learning](https://mlsanity.com/paper/1902.00183/) (2019)
- [Safe Reinforcement Learning via Curriculum Induction](https://mlsanity.com/paper/2006.12136/) (2020)
- [Multi-Modal Imitation Learning from Unstructured Demonstrations using Generative Adversarial Nets](https://mlsanity.com/paper/1705.10479/) (2017)

## Built on by (most cited first, 6 of 6)

- [A Review of Safe Reinforcement Learning: Methods, Theory and Applications](https://mlsanity.com/paper/2205.10330/) (2022)
- [Deep Generative Models for Offline Policy Learning: Tutorial, Survey, and Perspectives on Future Directions](https://mlsanity.com/paper/2402.13777/) (2024)
- [Enhancing Efficiency of Safe Reinforcement Learning via Sample Manipulation](https://mlsanity.com/paper/2405.20860/) (2024)
- [Data Valuation for Offline Reinforcement Learning](https://mlsanity.com/paper/2205.09550/) (2022)
- [Enhancing Offline Reinforcement Learning with Curriculum Learning-Based Trajectory Valuation](https://mlsanity.com/paper/2502.00601/) (2025)
- [Skill-based Safe Reinforcement Learning with Risk Planning](https://mlsanity.com/paper/2505.01619/) (2025)

## Abstract (arXiv)

Methods that extract policy primitives from offline demonstrations using deep generative models have shown promise at accelerating reinforcement learning(RL) for new tasks. Intuitively, these methods should also help to trainsafeRLagents because they enforce useful skills. However, we identify these techniques are not well equipped for safe policy learning because they ignore negative experiences(e.g., unsafe or unsuccessful), focusing only on positive experiences, which harms their ability to generalize to new tasks safely. Rather, we model the latentsafetycontextusing principled contrastive training on an offline dataset of demonstrations from many tasks, including both negative and positive experiences. Using this late variable, our RL framework, SAFEty skill pRiors (SAFER) extracts task-specific safe primitive skills to safely and successfully generalize to new tasks. In the inference stage, policies trained with SAFER learn to compose safe skills into successful policies. We theoretically characterize why SAFER can enforce safe policy learning and demonstrate its effectiveness on several complex safety-critical robotic grasping tasks inspired by the game Operation, in which SAFERoutperforms state-of-the-art primitive learning methods in success and safety.