# Dual Action Policy for Robust Sim-to-Real Reinforcement Learning

arXiv: https://arxiv.org/abs/2410.12250 · HTML: https://mlsanity.com/paper/2410.12250/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Safe and constrained RL, one of 15 directions in Deep reinforcement learning methods.
- Builds on 21 of its 29 references that are in the map.
- First posted on arXiv 16 Oct 2024.

## Placed in

- Deep reinforcement learning methods / [Safe and constrained RL](https://mlsanity.com/deeprl/safe-and-constrained-rl/)

## Builds on (most cited first, 21 of 21)

- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Soft Actor-Critic Algorithms and Applications](https://mlsanity.com/paper/1812.05905/) (2018)
- [Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models](https://mlsanity.com/paper/1805.12114/) (2018)
- [When to Trust Your Model: Model-Based Policy Optimization](https://mlsanity.com/paper/1906.08253/) (2019)
- [Sim-to-Real Transfer of Robotic Control with Dynamics Randomization](https://mlsanity.com/paper/1710.06537/) (2017)
- [Reinforcement Learning with Deep Energy-Based Policies](https://mlsanity.com/paper/1702.08165/) (2017)
- [Learning Quadrupedal Locomotion over Challenging Terrain](https://mlsanity.com/paper/2010.11251/) (2020)
- [Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updates](https://mlsanity.com/paper/1610.00633/) (2016)
- [Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble](https://mlsanity.com/paper/2110.01548/) (2021)
- [Model-Ensemble Trust-Region Policy Optimization](https://mlsanity.com/paper/1802.10592/) (2018)
- [Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experience](https://mlsanity.com/paper/1810.05687/) (2018)
- [Preparing for the Unknown: Learning a Universal Policy with Online System Identification](https://mlsanity.com/paper/1702.02453/) (2017)
- [Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers](https://mlsanity.com/paper/2006.13916/) (2020)
- [Why So Pessimistic? Estimating Uncertainties for Offline RL through Ensembles, and Why Their Independence Matters](https://mlsanity.com/paper/2205.13703/) (2022)
- [Reward Uncertainty for Exploration in Preference-based Reinforcement Learning](https://mlsanity.com/paper/2205.12401/) (2022)
- [When to Trust Your Simulator: Dynamics-Aware Hybrid Offline-and-Online Reinforcement Learning](https://mlsanity.com/paper/2206.13464/) (2022)
- [Reinforcement Learning in Economics and Finance](https://mlsanity.com/paper/2003.10014/) (2020)
- [Transfer from Simulation to Real World through Learning Deep Inverse Dynamics Model](https://mlsanity.com/paper/1610.03518/) (2016)
- [SimGAN: Hybrid Simulator Identification for Domain Adaptation via Adversarial Reinforcement Learning](https://mlsanity.com/paper/2101.06005/) (2021)
- [Reinforced Grounded Action Transformation for Sim-to-Real Transfer](https://mlsanity.com/paper/2008.01279/) (2020)

## Abstract (arXiv)

This paper presents Dual Action Policy (DAP), a novel approach to address the dynamics mismatch inherent in the sim-to-real gap of reinforcement learning. DAP uses a single policy to predict two sets of actions: one for maximizing task rewards in simulation and another specifically for domain adaptation via reward adjustments. This decoupling makes it easier to maximize the overall reward in the source domain during training. Additionally, DAP incorporates uncertainty-based exploration during training to enhance agent robustness. Experimental results demonstrate DAP's effectiveness in bridging the sim-to-real gap, outperforming baselines on challenging tasks in simulation, and further improvement is achieved by incorporating uncertainty estimation.