# Physically-Grounded Goal Imagination: Physics-Informed Variational Autoencoder for Self-Supervised Reinforcement Learning

arXiv: https://arxiv.org/abs/2511.06745 · HTML: https://mlsanity.com/paper/2511.06745/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods.
- Builds on 13 of its 20 references that are in the map.
- First posted on arXiv 10 Nov 2025.

## Placed in

- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 13 of 13)

- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Hindsight Experience Replay](https://mlsanity.com/paper/1707.01495/) (2017)
- [Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research](https://mlsanity.com/paper/1802.09464/) (2018)
- [Visual Reinforcement Learning with Imagined Goals](https://mlsanity.com/paper/1807.04742/) (2018)
- [Skew-Fit: State-Covering Self-Supervised Reinforcement Learning](https://mlsanity.com/paper/1903.03698/) (2019)
- [Physics-Integrated Variational Autoencoders for Robust and Interpretable Generative Modeling](https://mlsanity.com/paper/2102.13156/) (2021)
- [Contextual Imagined Goals for Self-Supervised Robotic Learning](https://mlsanity.com/paper/1910.11670/) (2019)
- [PI-VAE: Physics-Informed Variational Auto-Encoder for stochastic differential equations](https://mlsanity.com/paper/2203.11363/) (2022)
- [Phi-DVAE: Physics-Informed Dynamical Variational Autoencoders for Unstructured Data Assimilation](https://mlsanity.com/paper/2209.15609/) (2022)
- [Physics-informed Variational Autoencoders for Improved Robustness to Environmental Factors of Variation](https://mlsanity.com/paper/2210.10418/) (2022)
- [PITA: Physics-Informed Trajectory Autoencoder](https://mlsanity.com/paper/2403.11728/) (2024)

## Abstract (arXiv)

Self-supervised goal-conditioned reinforcement learning enables robots to autonomously acquire diverse skills without human supervision. However, a central challenge is the goal setting problem: robots must propose feasible and diverse goals that are achievable in their current environment. Existing methods like RIG (Visual Reinforcement Learning with Imagined Goals) use variational autoencoder (VAE) to generate goals in a learned latent space but have the limitation of producing physically implausible goals that hinder learning efficiency. We propose Physics-Informed RIG (PI-RIG), which integrates physical constraints directly into the VAE training process through a novel Enhanced Physics-Informed Variational Autoencoder (Enhanced p3-VAE), enabling the generation of physically consistent and achievable goals. Our key innovation is the explicit separation of the latent space into physics variables governing object dynamics and environmental factors capturing visual appearance, while enforcing physical consistency through differential equation constraints and conservation laws. This enables the generation of physically consistent and achievable goals that respect fundamental physical principles such as object permanence, collision constraints, and dynamic feasibility. Through extensive experiments, we demonstrate that this physics-informed goal generation significantly improves the quality of proposed goals, leading to more effective exploration and better skill acquisition in visual robotic manipulation tasks including reaching, pushing, and pick-and-place scenarios.