# Contrastive Variational Reinforcement Learning for Complex Observations

arXiv: https://arxiv.org/abs/2008.02430 · HTML: https://mlsanity.com/paper/2008.02430/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Aug 2020.

## Built on by (most cited first, 15 of 15)

- [Temporal Predictive Coding For Model-Based Planning In Latent Space](https://mlsanity.com/paper/2106.07156/) (2021)
- [DreamingV2: Reinforcement Learning with Discrete World Models without Reconstruction](https://mlsanity.com/paper/2203.00494/) (2022)
- [INFOrmation Prioritization through EmPOWERment in Visual Model-Based RL](https://mlsanity.com/paper/2204.08585/) (2022)
- [The Free Energy Principle for Perception and Action: A Deep Learning Perspective](https://mlsanity.com/paper/2207.06415/) (2022)
- [Contrastive Active Inference](https://mlsanity.com/paper/2110.10083/) (2021)
- [Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels](https://mlsanity.com/paper/2209.12016/) (2022)
- [Learning Latent Graph Dynamics for Visual Manipulation of Deformable Objects](https://mlsanity.com/paper/2104.12149/) (2021)
- [Multi-Modal Mutual Information (MuMMI) Training for Robust Self-Supervised Deep Reinforcement Learning](https://mlsanity.com/paper/2107.02339/) (2021)
- [Learning Visual Shape Control of Novel 3D Deformable Objects from Partial-View Point Clouds](https://mlsanity.com/paper/2110.04685/) (2021)
- [Model-Value Inconsistency as a Signal for Epistemic Uncertainty](https://mlsanity.com/paper/2112.04153/) (2021)
- [Multi-View Dreaming: Multi-View World Model with Contrastive Learning](https://mlsanity.com/paper/2203.11024/) (2022)
- [DeformerNet: Learning Bimanual Manipulation of 3D Deformable Objects](https://mlsanity.com/paper/2305.04449/) (2023)
- [Review of Metrics to Measure the Stability, Robustness and Resilience of Reinforcement Learning](https://mlsanity.com/paper/2203.12048/) (2022)
- [Imitation Learning via Differentiable Physics](https://mlsanity.com/paper/2206.04873/) (2022)
- [CURLing the Dream: Contrastive Representations for World Modeling in Reinforcement Learning](https://mlsanity.com/paper/2408.05781/) (2024)

## Abstract (arXiv)

Deep reinforcement learning (DRL) has achieved significant success in various robot tasks: manipulation, navigation, etc. However, complex visual observations in natural environments remains a major challenge. This paper presents Contrastive Variational Reinforcement Learning (CVRL), a model-based method that tackles complex visual observations in DRL. CVRL learns a contrastive variational model by maximizing the mutual information between latent states and observations discriminatively, through contrastive learning. It avoids modeling the complex observation space unnecessarily, as the commonly used generative observation model often does, and is significantly more robust. CVRL achieves comparable performance with state-of-the-art model-based DRL methods on standard Mujoco tasks. It significantly outperforms them on Natural Mujoco tasks and a robot box-pushing task with complex observations, e.g., dynamic shadows. The CVRL code is available publicly at https://github.com/Yusufma03/CVRL.