# Off Environment Evaluation Using Convex Risk Minimization

arXiv: https://arxiv.org/abs/2112.11532 · HTML: https://mlsanity.com/paper/2112.11532/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 32 references that are in the map.
- First posted on arXiv 21 Dec 2021.

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

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [Hindsight Experience Replay](https://mlsanity.com/paper/1707.01495/) (2017)
- [End-to-End Training of Deep Visuomotor Policies](https://mlsanity.com/paper/1504.00702/) (2015)
- [Deep Reinforcement Learning that Matters](https://mlsanity.com/paper/1709.06560/) (2017)
- [Solving Rubik's Cube with a Robot Hand](https://mlsanity.com/paper/1910.07113/) (2019)
- [Sim-to-Real Transfer of Robotic Control with Dynamics Randomization](https://mlsanity.com/paper/1710.06537/) (2017)
- [Doubly Robust Off-policy Value Evaluation for Reinforcement Learning](https://mlsanity.com/paper/1511.03722/) (2015)
- [Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning](https://mlsanity.com/paper/1604.00923/) (2016)
- [DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution Corrections](https://mlsanity.com/paper/1906.04733/) (2019)
- [Batch Policy Learning under Constraints](https://mlsanity.com/paper/1903.08738/) (2019)
- [Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation](https://mlsanity.com/paper/1810.12429/) (2018)
- [Minimax Weight and Q-Function Learning for Off-Policy Evaluation](https://mlsanity.com/paper/1910.12809/) (2019)
- [More Robust Doubly Robust Off-policy Evaluation](https://mlsanity.com/paper/1802.03493/) (2018)
- [Empirical Study of Off-Policy Policy Evaluation for Reinforcement Learning](https://mlsanity.com/paper/1911.06854/) (2019)
- [Combining Planning and Deep Reinforcement Learning in Tactical Decision Making for Autonomous Driving](https://mlsanity.com/paper/1905.02680/) (2019)
- [Importance Sampling Policy Evaluation with an Estimated Behavior Policy](https://mlsanity.com/paper/1806.01347/) (2018)
- [Deep Reinforcement Learning based Recommendation with Explicit User-Item Interactions Modeling](https://mlsanity.com/paper/1810.12027/) (2018)
- [Adapting Deep Visuomotor Representations with Weak Pairwise Constraints](https://mlsanity.com/paper/1511.07111/) (2015)
- [Perspectives on Sim2Real Transfer for Robotics: A Summary of the R:SS 2020 Workshop](https://mlsanity.com/paper/2012.03806/) (2020)
- [Improved Robustness and Safety for Autonomous Vehicle Control with Adversarial Reinforcement Learning](https://mlsanity.com/paper/1903.03642/) (2019)
- [Robot Sound Interpretation: Combining Sight and Sound in Learning-Based Control](https://mlsanity.com/paper/1909.09172/) (2019)

## Built on by (most cited first, 2 of 2)

- [Marginalized Importance Sampling for Off-Environment Policy Evaluation](https://mlsanity.com/paper/2309.01807/) (2023)
- [Towards Provable Log Density Policy Gradient](https://mlsanity.com/paper/2403.01605/) (2024)

## Abstract (arXiv)

Applying reinforcement learning (RL) methods on robots typically involves training a policy in simulation and deploying it on a robot in the real world. Because of the model mismatch between the real world and the simulator, RL agents deployed in this manner tend to perform suboptimally. To tackle this problem, researchers have developed robust policy learning algorithms that rely on synthetic noise disturbances. However, such methods do not guarantee performance in the target environment. We propose a convex risk minimization algorithm to estimate the model mismatch between the simulator and the target domain using trajectory data from both environments. We show that this estimator can be used along with the simulator to evaluate performance of an RL agents in the target domain, effectively bridging the gap between these two environments. We also show that the convergence rate of our estimator to be of the order of n-1/4, where n is the number of training samples. In simulation, we demonstrate how our method effectively approximates and evaluates performance on Gridworld, Cartpole, and Reacher environments on a range of policies. We also show that the our method is able to estimate performance of a 7 DOF robotic arm using the simulator and remotely collected data from the robot in the real world.