More Like this

1. Learning from Active Human Involvement through Proxy Value Propagation

   Peng, Zhenghao ; Mo, Wenjie ; Duan, Chenda ; Li, Quanyi ; Zhou, Bolei. ( December 2023 , Advances in neural information processing systems)

   Learning from active human involvement enables the human subject to actively intervene and demonstrate to the AI agent during training. The interaction and corrective feedback from human brings safety and AI alignment to the learning process. In this work, we propose a new reward-free active human involvement method called Proxy Value Propagation for policy optimization. Our key insight is that a proxy value function can be designed to express human intents, wherein state- action pairs in the human demonstration are labeled with high values, while those agents’ actions that are intervened receive low values. Through the TD-learning framework, labeled values of demonstrated state-action pairs are further propagated to other unlabeled data generated from agents’ exploration. The proxy value function thus induces a policy that faithfully emulates human behaviors. Human- in-the-loop experiments show the generality and efficiency of our method. With minimal modification to existing reinforcement learning algorithms, our method can learn to solve continuous and discrete control tasks with various human control devices, including the challenging task of driving in Grand Theft Auto V. Demo video and code are available at: https://metadriverse.github.io/pvp. 

   more » « less
2. Q-Functionals For Value-Based Continuous Control

   Lobel, S ; Rammohan, S ; He, B ; Yu, S ; Konidaris, GD ( February 2023 , Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence)

   We present Q-functionals, an alternative architecture for continuous control deep reinforcement learning. Instead of returning a single value for a state-action pair, our network transforms a state into a function that can be rapidly evaluated in parallel for many actions, allowing us to efficiently choose high-value actions through sampling. This contrasts with the typical architecture of off-policy continuous control, where a policy network is trained for the sole purpose of selecting actions from the Q-function. We represent our action-dependent Q-function as a weighted sum of basis functions (Fourier, Polynomial, etc) over the action space, where the weights are state-dependent and output by the Q-functional network. Fast sampling makes practical a variety of techniques that require Monte-Carlo integration over Q-functions, and enables action-selection strategies besides simple value-maximization. We characterize our framework, describe various implementations of Q-functionals, and demonstrate strong performance on a suite of continuous control tasks. 

   more » « less
3. Residual Policy Learning for Shared Autonomy

   Schaff, Charles ; Walter, Matthew R. ( July 2020 , Proceedings of Robotics: Science and Systems (RSS))

   Shared autonomy provides an effective framework for human-robot collaboration that takes advantage of the complementary strengths of humans and robots to achieve common goals. Many existing approaches to shared autonomy make restrictive assumptions that the goal space, environment dynamics, or human policy are known a priori, or are limited to discrete action spaces, preventing those methods from scaling to complicated real world environments. We propose a model-free, residual policy learning algorithm for shared autonomy that alleviates the need for these assumptions. Our agents are trained to minimally adjust the human’s actions such that a set of goal-agnostic constraints are satisfied. We test our method in two continuous control environments: Lunar Lander, a 2D flight control domain, and a 6-DOF quadrotor reaching task. In experiments with human and surrogate pilots, our method significantly improves task performance without any knowledge of the human’s goal beyond the constraints. These results highlight the ability of model-free deep reinforcement learning to realize assistive agents suited to continuous control settings with little knowledge of user intent. 

   more » « less
4. Statistical Inference of the Value Function for Reinforcement Learning in Infinite-Horizon Settings

   https://doi.org/10.1111/rssb.12465  

   Shi, Chengchun ; Zhang, Sheng ; Lu, Wenbin ; Song, Rui ( December 2021 , Journal of the Royal Statistical Society Series B: Statistical Methodology)

   Reinforcement learning is a general technique that allows an agent to learn an optimal policy and interact with an environment in sequential decision-making problems. The goodness of a policy is measured by its value function starting from some initial state. The focus of this paper was to construct confidence intervals (CIs) for a policy’s value in infinite horizon settings where the number of decision points diverges to infinity. We propose to model the action-value state function (Q-function) associated with a policy based on series/sieve method to derive its confidence interval. When the target policy depends on the observed data as well, we propose a SequentiAl Value Evaluation (SAVE) method to recursively update the estimated policy and its value estimator. As long as either the number of trajectories or the number of decision points diverges to infinity, we show that the proposed CI achieves nominal coverage even in cases where the optimal policy is not unique. Simulation studies are conducted to back up our theoretical findings. We apply the proposed method to a dataset from mobile health studies and find that reinforcement learning algorithms could help improve patient’s health status. A Python implementation of the proposed procedure is available at https://github.com/shengzhang37/SAVE.

    

   more » « less
5. Optimistic Initialization for Exploration in Continuous Control

   Lobel, S ; Bagaria, A ; Allen, C ; Gottesman, O ; Konidaris, G.D. ( February 2022 , Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence)

   Optimistic initialization underpins many theoretically sound exploration schemes in tabular domains; however, in the deep function approximation setting, optimism can quickly disappear if initialized naively. We propose a framework for more effectively incorporating optimistic initialization into reinforcement learning for continuous control. Our approach uses metric information about the state-action space to estimate which transitions are still unexplored, and explicitly maintains the initial Q-value optimism for the corresponding state-action pairs. We also develop methods for efficiently approximating these training objectives, and for incorporating domain knowledge into the optimistic envelope to improve sample efficiency. We empirically evaluate these approaches on a variety of hard exploration problems in continuous control, where our method outperforms existing exploration techniques. 

   more » « less