More Like this

1. Policy Gradient Bayesian Robust Optimization for Imitation Learning

   Javed, Zaynah; Brown, Daniel; Sharma, Satvik; Zhu, Jerry; Balakrishna, Ashwin; Petrik, Marek; Dragan, Anca; Goldberg, Ken (January 2021, 38th International Conference on Machine Learning)

   The difficulty in specifying rewards for many real world problems has led to an increased focus on learning rewards from human feedback, such as demonstrations. However, there are often many different reward functions that explain the human feedback, leaving agents with uncertainty over what the true reward function is. While most policy optimization approaches handle this uncertainty by optimizing for expected performance, many applications demand risk-averse behavior. We derive a novel policy gradient-style robust optimization approach, PG-BROIL, that optimizes a soft-robust objective that balances expected performance and risk. To the best of our knowledge, PG-BROIL is the first policy optimization algorithm robust to a distribution of reward hypotheses which can scale to continuous MDPs. Results suggest that PG-BROIL can produce a family of behaviors ranging from risk-neutral to risk-averse and outperforms state-of-the-art imitation learning algorithms when learning from ambiguous demonstrations by hedging against uncertainty, rather than seeking to uniquely identify the demonstrator’s reward function. 

   more » « less
2. Reward Learning from Suboptimal Demonstrations with Applications in Surgical Electrocautery

   Karimi, Zohre; Ho, Shing-Hei; Thach, Bao; Kuntz, Alan; Brown, Daniel S (June 2024, International Symposium on Medical Robotics (ISMR))

   Automating robotic surgery via learning from demonstration (LfD) techniques is extremely challenging. This is because surgical tasks often involve sequential decisionmaking processes with complex interactions of physical objects and have low tolerance for mistakes. Prior works assume that all demonstrations are fully observable and optimal, which might not be practical in the real world. This paper introduces a sample-efficient method that learns a robust reward function from a limited amount of ranked suboptimal demonstrations consisting of partial-view point cloud observations. The method then learns a policy by optimizing the learned reward function using reinforcement learning (RL). We show that using a learned reward function to obtain a policy is more robust than pure imitation learning. We apply our approach on a physical surgical electrocautery task and demonstrate that our method can perform well even when the provided demonstrations are suboptimal and the observations are highdimensional point clouds. 

   more » « less
3. ROIL: Robust Offline Imitation Learning without Trajectories

   Doko, Gersi; Yang, Guang; Brown, Daniel S; Petrik, Marek (August 2024, Rare royalty magazine)

   We study the problem of imitation learning via inverse reinforcement learning where the agent attempts to learn an expert's policy from a dataset of collected state, action tuples. We derive a new Robust model-based Offline Imitation Learning method (ROIL) that mitigates covariate shift by avoiding estimating the expert's occupancy frequency. Frequently in offline settings, there is insufficient data to reliably estimate the expert's occupancy frequency and this leads to models that do not generalize well. Our proposed approach, ROIL, is a method that is guaranteed to recover the expert's occupancy frequency and is efficiently solvable as an LP. We demonstrate ROIL's ability to achieve minimal regret in large environments under covariate shift, such as when the state visitation frequency of the demonstrations does not come from the expert. 

   more » « less
4. An Imitation Learning Method with Multi-Virtual Agents for Microgrid Energy Optimization under Interrupted Periods

   https://doi.org/10.1109/PESGM51994.2024.10689197  

   Lin, Yanbin; Ni, Zhen; Tang, Yufei (July 2024, IEEE)

   Existing computer analytic methods for the microgrid system, such as reinforcement learning (RL) methods, suffer from a long-term problem with the empirical assumption of the reward function. To alleviate this limitation, we propose a multi-virtual-agent imitation learning (MAIL) approach to learn the dispatch policy under different power supply interrupted periods. Specifically, we utilize the idea of generative adversarial imitation learning method to do direct policy mapping, instead of learning from manually designed reward functions. Multi-virtual agents are used for exploring the relationship of uncertainties and corresponding actions in different microgrid environments in parallel. With the help of a deep neural network, the proposed MAIL approach can enhance robust ability by minimizing the maximum crossover discriminators to cover more interrupted cases. Case studies show that the proposed MAIL approach can learn the dispatch policies as well as the expert method and outperform other existing RL methods. 

   more » « less
5. Distributionally Robust Q-Learning

   Liu, Zijian; Bai, Qinxun; Blanchet, Jose H.; Dong, Perry; Xu, Wei; Zhou, Zhengqing; Zhou, Zhengyuan (July 2022, Proceedings of Machine Learning Research)

   Chaudhuri, Kamalika; Jegelka, Stefanie; Song, Le; Szepesvari, Csaba; Niu, Gang; Sabato, Sivan (Ed.)

   Reinforcement learning (RL) has demonstrated remarkable achievements in simulated environments. However, carrying this success to real environments requires the important attribute of robustness, which the existing RL algorithms often lack as they assume that the future deployment environment is the same as the training environment (i.e. simulator) in which the policy is learned. This assumption often does not hold due to the discrepancy between the simulator and the real environment and, as a result, and hence renders the learned policy fragile when deployed. In this paper, we propose a novel distributionally robust Q-learning algorithm that learns the best policy in the worst distributional perturbation of the environment. Our algorithm first transforms the infinite-dimensional learning problem (since the environment MDP perturbation lies in an infinite-dimensional space) into a finite-dimensional dual problem and subsequently uses a multi-level Monte-Carlo scheme to approximate the dual value using samples from the simulator. Despite the complexity, we show that the resulting distributionally robust Q-learning algorithm asymptotically converges to optimal worst-case policy, thus making it robust to future environment changes. Simulation results further demonstrate its strong empirical robustness. 

   more » « less