Residual-MPPI: Online Policy Customization for Continuous Control

Policies learned through Reinforcement Learning (RL) and Imitation Learning (IL) have demonstrated significant potential in achieving advanced performance in continuous control tasks. However, in real-world environments, it is often necessary to further customize a trained policy when there are additional requirements that were unforeseen during the original training phase. It is possible to fine-tune the policy to meet the new requirements, but this often requires collecting new data with the added requirements and access to the original training metric and policy parameters. In contrast, an online planning algorithm, if capable of meeting the additional requirements, can eliminate the necessity for extensive training phases and customize the policy without knowledge of the original training scheme or task. In this work, we propose a generic online planning algorithm for customizing continuous-control policies at the execution time which we call Residual-MPPI. It is able to customize a given prior policy on new performance metrics in few-shot and even zero-shot online settings. Also, Residual-MPPI only requires access to the action distribution produced by the prior policy, without additional knowledge regarding the original task. Through our experiments, we demonstrate that the proposed Residual-MPPI algorithm can accomplish the few-shot/zero-shot online policy customization task effectively, including customizing the champion-level racing agent, Gran Turismo Sophy (GT Sophy) 1.0, in the challenging car racing scenario, Gran Turismo Sport (GTS) environment. Demo videos are available on our website: https://sites.google.com/view/residual-mppi

BeTAIL: Behavior Transformer Adversarial Imitation Learning from Human Racing Gameplay

Imitation learning learns a policy from demonstrations without requiring hand-designed reward functions. In many robotic tasks, such as autonomous racing, imitated policies must model complex environment dynamics and human decision-making. Sequence modeling is highly effective in capturing intricate patterns of motion sequences but struggles to adapt to new environments or distribution shifts that are common in real-world robotics tasks. In contrast, Adversarial Imitation Learning (AIL) can mitigate this effect, but struggles with sample inefficiency and handling complex motion patterns. Thus, we propose BeTAIL: Behavior Transformer Adversarial Imitation Learning, which combines a Behavior Transformer (BeT) policy from human demonstrations with online AIL. BeTAIL adds an AIL residual policy to the BeT policy to model the sequential decision-making process of human experts and correct for out-of-distribution states or shifts in environment dynamics. We test BeTAIL on three challenges with expert-level demonstrations of real human gameplay in Gran Turismo Sport. Our proposed residual BeTAIL reduces environment interactions and improves racing performance and stability, even when the BeT is pretrained on different tracks than downstream learning. Videos and code available at: https://sites.google.com/berkeley.edu/BeTAIL/home.

Skill-Critic: Refining Learned Skills for Reinforcement Learning

Hierarchical reinforcement learning (RL) can accelerate long-horizon decision-making by temporally abstracting a policy into multiple levels. Promising results in sparse reward environments have been seen with skills, i.e. sequences of primitive actions. Typically, a skill latent space and policy are discovered from offline data, but the resulting low-level policy can be unreliable due to low-coverage demonstrations or distribution shifts. As a solution, we propose fine-tuning the low-level policy in conjunction with high-level skill selection. Our Skill-Critic algorithm optimizes both the low and high-level policies; these policies are also initialized and regularized by the latent space learned from offline demonstrations to guide the joint policy optimization. We validate our approach in multiple sparse RL environments, including a new sparse reward autonomous racing task in Gran Turismo Sport. The experiments show that Skill-Critic's low-level policy fine-tuning and demonstration-guided regularization are essential for optimal performance. Images and videos are available at https://sites.google.com/view/skill-critic. We plan to open source the code with the final version.

Double-Iterative Gaussian Process Regression for Modeling Error Compensation in Autonomous Racing

Autonomous racing control is a challenging research problem as vehicles are pushed to their limits of handling to achieve an optimal lap time; therefore, vehicles exhibit highly nonlinear and complex dynamics. Difficult-to-model effects, such as drifting, aerodynamics, chassis weight transfer, and suspension can lead to infeasible and suboptimal trajectories. While offline planning allows optimizing a full reference trajectory for the minimum lap time objective, such modeling discrepancies are particularly detrimental when using offline planning, as planning model errors compound with controller modeling errors. Gaussian Process Regression (GPR) can compensate for modeling errors. However, previous works primarily focus on modeling error in real-time control without consideration for how the model used in offline planning can affect the overall performance. In this work, we propose a double-GPR error compensation algorithm to reduce model uncertainties; specifically, we compensate both the planner's model and controller's model with two respective GPR-based error compensation functions. Furthermore, we design an iterative framework to re-collect error-rich data using the racing control system. We test our method in the high-fidelity racing simulator Gran Turismo Sport (GTS); we find that our iterative, double-GPR compensation functions improve racing performance and iteration stability in comparison to a single compensation function applied merely for real-time control.

Outracing Human Racers with Model-based Autonomous Racing

Autonomous racing has become a popular sub-topic of autonomous driving in recent years. The goal of autonomous racing research is to develop software to control the vehicle at its limit of handling and achieve human-level racing performance. In this work, we investigate how to approach human expert-level racing performance with model-based planning and control methods using the high-fidelity racing simulator Gran Turismo Sport (GTS). GTS enables a unique opportunity for autonomous racing research, as many recordings of racing from highly skilled human players can served as expert emonstrations. By comparing the performance of the autonomous racing software with human experts, we better understand the performance gap of existing software and explore new methodologies in a principled manner. In particular, we focus on the commonly adopted model-based racing framework, consisting of an offline trajectory planner and an online Model Predictive Control-based (MPC) tracking controller. We thoroughly investigate the design challenges from three perspective, namely vehicle model, planning algorithm, and controller design, and propose novel solutions to improve the baseline approach toward human expert-level performance. We showed that the proposed control framework can achieve top 0.95% lap time among human-expert players in GTS. Furthermore, we conducted comprehensive ablation studies to validate the necessity of proposed modules, and pointed out potential future directions to reach human-best performance.