# PAnDR: Fast Adaptation to New Environments from Offline Experiences via Decoupling Policy and Environment Representations

arXiv: https://arxiv.org/abs/2204.02877 · HTML: https://mlsanity.com/paper/2204.02877/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 34 references that are in the map.
- First posted on arXiv 6 Apr 2022.

## Builds on (most cited first, 23 of 23)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [CURL: Contrastive Unsupervised Representations for Reinforcement Learning](https://mlsanity.com/paper/2004.04136/) (2020)
- [Learning Dexterous In-Hand Manipulation](https://mlsanity.com/paper/1808.00177/) (2018)
- [Sim-to-Real Transfer of Robotic Control with Dynamics Randomization](https://mlsanity.com/paper/1710.06537/) (2017)
- [Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels](https://mlsanity.com/paper/2004.13649/) (2020)
- [On Variational Bounds of Mutual Information](https://mlsanity.com/paper/1905.06922/) (2019)
- [RL2: Fast Reinforcement Learning via Slow Reinforcement Learning](https://mlsanity.com/paper/1611.02779/) (2016)
- [Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables](https://mlsanity.com/paper/1903.08254/) (2019)
- [Agent57: Outperforming the Atari Human Benchmark](https://mlsanity.com/paper/2003.13350/) (2020)
- [CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information](https://mlsanity.com/paper/2006.12013/) (2020)
- [Assessing Generalization in Deep Reinforcement Learning](https://mlsanity.com/paper/1810.12282/) (2018)
- [Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learning](https://mlsanity.com/paper/2004.14646/) (2020)
- [Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning](https://mlsanity.com/paper/2005.06800/) (2020)
- [Meta-Q-Learning](https://mlsanity.com/paper/1910.00125/) (2019)
- [Improving black-box optimization in VAE latent space using decoder uncertainty](https://mlsanity.com/paper/2107.00096/) (2021)
- [Learning Policy Representations in Multiagent Systems](https://mlsanity.com/paper/1806.06464/) (2018)
- [Towards Effective Context for Meta-Reinforcement Learning: an Approach based on Contrastive Learning](https://mlsanity.com/paper/2009.13891/) (2020)
- [Policy Evaluation Networks](https://mlsanity.com/paper/2002.11833/) (2020)
- [Parameter-Based Value Functions](https://mlsanity.com/paper/2006.09226/) (2020)
- [Automatic Web Testing using Curiosity-Driven Reinforcement Learning](https://mlsanity.com/paper/2103.06018/) (2021)

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

- [Position: Foundation Agents as the Paradigm Shift for Decision Making](https://mlsanity.com/paper/2405.17009/) (2024)
- [Towards A Unified Policy Abstraction Theory and Representation Learning Approach in Markov Decision Processes](https://mlsanity.com/paper/2209.07696/) (2022)
- [Prioritized Trajectory Replay: A Replay Memory for Data-driven Reinforcement Learning](https://mlsanity.com/paper/2306.15503/) (2023)
- [Decomposed Mutual Information Optimization for Generalized Context in Meta-Reinforcement Learning](https://mlsanity.com/paper/2210.04209/) (2022)
- [Skill-aware Mutual Information Optimisation for Generalisation in Reinforcement Learning](https://mlsanity.com/paper/2406.04815/) (2024)
- [Implicit Neural Representations of Individual Behavior](https://mlsanity.com/paper/2606.12200/) (2026)

## Abstract (arXiv)

Deep Reinforcement Learning (DRL) has been a promising solution to many complex decision-making problems. Nevertheless, the notorious weakness in generalization among environments prevent widespread application of DRL agents in real-world scenarios. Although advances have been made recently, most prior works assume sufficient online interaction on training environments, which can be costly in practical cases. To this end, we focus on an offline-training-online-adaptation setting, in which the agent first learns from offline experiences collected in environments with different dynamics and then performs online policy adaptation in environments with new dynamics. In this paper, we propose Policy Adaptation with Decoupled Representations (PAnDR) for fast policy adaptation. In offline training phase, the environment representation and policy representation are learned through contrastive learning and policy recovery, respectively. The representations are further refined by mutual information optimization to make them more decoupled and complete. With learned representations, a Policy-Dynamics Value Function (PDVF) [Raileanu et al., 2020] network is trained to approximate the values for different combinations of policies and environments from offline experiences. In online adaptation phase, with the environment context inferred from few experiences collected in new environments, the policy is optimized by gradient ascent with respect to the PDVF. Our experiments show that PAnDR outperforms existing algorithms in several representative policy adaptation problems.