BECAUSE: Bilinear Causal Representation for Generalizable Offline Model-based Reinforcement Learning

Offline model-based reinforcement learning (MBRL) enhances data efficiency by utilizing pre-collected datasets to learn models and policies, especially in scenarios where exploration is costly or infeasible. Nevertheless, its performance often suffers from the objective mismatch between model and policy learning, resulting in inferior performance despite accurate model predictions. This paper first identifies the primary source of this mismatch comes from the underlying confounders present in offline data for MBRL. Subsequently, we introduce \textbf{B}ilin\textbf{E}ar \textbf{CAUS}al r\textbf{E}presentation~(BECAUSE), an algorithm to capture causal representation for both states and actions to reduce the influence of the distribution shift, thus mitigating the objective mismatch problem. Comprehensive evaluations on 18 tasks that vary in data quality and environment context demonstrate the superior performance of BECAUSE over existing offline RL algorithms. We show the generalizability and robustness of BECAUSE under fewer samples or larger numbers of confounders. Additionally, we offer theoretical analysis of BECAUSE to prove its error bound and sample efficiency when integrating causal representation into offline MBRL.

CaDRE: Controllable and Diverse Generation of Safety-Critical Driving Scenarios using Real-World Trajectories

Simulation is an indispensable tool in the development and testing of autonomous vehicles (AVs), offering an efficient and safe alternative to road testing by allowing the exploration of a wide range of scenarios. Despite its advantages, a significant challenge within simulation-based testing is the generation of safety-critical scenarios, which are essential to ensure that AVs can handle rare but potentially fatal situations. This paper addresses this challenge by introducing a novel generative framework, CaDRE, which is specifically designed for generating diverse and controllable safety-critical scenarios using real-world trajectories. Our approach optimizes for both the quality and diversity of scenarios by employing a unique formulation and algorithm that integrates real-world data, domain knowledge, and black-box optimization techniques. We validate the effectiveness of our framework through extensive testing in three representative types of traffic scenarios. The results demonstrate superior performance in generating diverse and high-quality scenarios with greater sample efficiency than existing reinforcement learning and sampling-based methods.

RealGen: Retrieval Augmented Generation for Controllable Traffic Scenarios

Simulation plays a crucial role in the development of autonomous vehicles (AVs) due to the potential risks associated with real-world testing. Although significant progress has been made in the visual aspects of simulators, generating complex behavior among agents remains a formidable challenge. It is not only imperative to ensure realism in the scenarios generated but also essential to incorporate preferences and conditions to facilitate controllable generation for AV training and evaluation. Traditional methods, mainly relying on memorizing the distribution of training datasets, often fall short in generating unseen scenarios. Inspired by the success of retrieval augmented generation in large language models, we present RealGen, a novel retrieval-based in-context learning framework for traffic scenario generation. RealGen synthesizes new scenarios by combining behaviors from multiple retrieved examples in a gradient-free way, which may originate from templates or tagged scenarios. This in-context learning framework endows versatile generative capabilities, including the ability to edit scenarios, compose various behaviors, and produce critical scenarios. Evaluations show that RealGen offers considerable flexibility and controllability, marking a new direction in the field of controllable traffic scenario generation. Check our project website for more information: https://realgen.github.io.

Safety-aware Causal Representation for Trustworthy Reinforcement Learning in Autonomous Driving

In the domain of autonomous driving, the Learning from Demonstration (LfD) paradigm has exhibited notable efficacy in addressing sequential decision-making problems. However, consistently achieving safety in varying traffic contexts, especially in safety-critical scenarios, poses a significant challenge due to the long-tailed and unforeseen scenarios absent from offline datasets. In this paper, we introduce the saFety-aware strUctured Scenario representatION (FUSION), a pioneering methodology conceived to facilitate the learning of an adaptive end-to-end driving policy by leveraging structured scenario information. FUSION capitalizes on the causal relationships between decomposed reward, cost, state, and action space, constructing a framework for structured sequential reasoning under dynamic traffic environments. We conduct rigorous evaluations in two typical real-world settings of distribution shift in autonomous vehicles, demonstrating the good balance between safety cost and utility reward of FUSION compared to contemporary state-of-the-art safety-aware LfD baselines. Empirical evidence under diverse driving scenarios attests that FUSION significantly enhances the safety and generalizability of autonomous driving agents, even in the face of challenging and unseen environments. Furthermore, our ablation studies reveal noticeable improvements in the integration of causal representation into the safe offline RL problem.

Seeing is not Believing: Robust Reinforcement Learning against Spurious Correlation

Robustness has been extensively studied in reinforcement learning (RL) to handle various forms of uncertainty such as random perturbations, rare events, and malicious attacks. In this work, we consider one critical type of robustness against spurious correlation, where different portions of the state do not have causality but have correlations induced by unobserved confounders. These spurious correlations are ubiquitous in real-world tasks, for instance, a self-driving car usually observes heavy traffic in the daytime and light traffic at night due to unobservable human activity. A model that learns such useless or even harmful correlation could catastrophically fail when the confounder in the test case deviates from the training one. Although motivated, enabling robustness against spurious correlation poses significant challenges since the uncertainty set, shaped by the unobserved confounder and sequential structure of RL, is difficult to characterize and identify. Existing robust algorithms that assume simple and unstructured uncertainty sets are therefore inadequate to address this challenge. To solve this issue, we propose Robust State-Confounded Markov Decision Processes (RSC-MDPs) and theoretically demonstrate its superiority in breaking spurious correlations compared with other robust RL counterparts. We also design an empirical algorithm to learn the robust optimal policy for RSC-MDPs, which outperforms all baselines in eight realistic self-driving and manipulation tasks.

What Went Wrong? Closing the Sim-to-Real Gap via Differentiable Causal Discovery

Training control policies in simulation is more appealing than on real robots directly, as it allows for exploring diverse states in a safe and efficient manner. Yet, robot simulators inevitably exhibit disparities from the real world, yielding inaccuracies that manifest as the simulation-to-real gap. Existing literature has proposed to close this gap by actively modifying specific simulator parameters to align the simulated data with real-world observations. However, the set of tunable parameters is usually manually selected to reduce the search space in a case-by-case manner, which is hard to scale up for complex systems and requires extensive domain knowledge. To address the scalability issue and automate the parameter-tuning process, we introduce an approach that aligns the simulator with the real world by discovering the causal relationship between the environment parameters and the sim-to-real gap. Concretely, our method learns a differentiable mapping from the environment parameters to the differences between simulated and real-world robot-object trajectories. This mapping is governed by a simultaneously-learned causal graph to help prune the search space of parameters, provide better interpretability, and improve generalization. We perform experiments to achieve both sim-to-sim and sim-to-real transfer, and show that our method has significant improvements in trajectory alignment and task success rate over strong baselines in a challenging manipulation task.

Your Room is not Private: Gradient Inversion Attack for Deep Q-Learning

The prominence of embodied Artificial Intelligence (AI), which empowers robots to navigate, perceive, and engage within virtual environments, has attracted significant attention, owing to the remarkable advancements in computer vision and large language models. Privacy emerges as a pivotal concern within the realm of embodied AI, as the robot access substantial personal information. However, the issue of privacy leakage in embodied AI tasks, particularly in relation to decision-making algorithms, has not received adequate consideration in research. This paper aims to address this gap by proposing an attack on the Deep Q-Learning algorithm, utilizing gradient inversion to reconstruct states, actions, and Q-values. The choice of using gradients for the attack is motivated by the fact that commonly employed federated learning techniques solely utilize gradients computed based on private user data to optimize models, without storing or transmitting the data to public servers. Nevertheless, these gradients contain sufficient information to potentially expose private data. To validate our approach, we conduct experiments on the AI2THOR simulator and evaluate our algorithm on active perception, a prevalent task in embodied AI. The experimental results convincingly demonstrate the effectiveness of our method in successfully recovering all information from the data across all 120 room layouts.

Bayesian Reparameterization of Reward-Conditioned Reinforcement Learning with Energy-based Models

Recently, reward-conditioned reinforcement learning (RCRL) has gained popularity due to its simplicity, flexibility, and off-policy nature. However, we will show that current RCRL approaches are fundamentally limited and fail to address two critical challenges of RCRL -- improving generalization on high reward-to-go (RTG) inputs, and avoiding out-of-distribution (OOD) RTG queries during testing time. To address these challenges when training vanilla RCRL architectures, we propose Bayesian Reparameterized RCRL (BR-RCRL), a novel set of inductive biases for RCRL inspired by Bayes' theorem. BR-RCRL removes a core obstacle preventing vanilla RCRL from generalizing on high RTG inputs -- a tendency that the model treats different RTG inputs as independent values, which we term ``RTG Independence". BR-RCRL also allows us to design an accompanying adaptive inference method, which maximizes total returns while avoiding OOD queries that yield unpredictable behaviors in vanilla RCRL methods. We show that BR-RCRL achieves state-of-the-art performance on the Gym-Mujoco and Atari offline RL benchmarks, improving upon vanilla RCRL by up to 11%.

Critical Scenario Generation for Developing Trustworthy Autonomy

Autonomous systems, such as self-driving vehicles, quadrupeds, and robot manipulators, are largely enabled by the rapid development of artificial intelligence. However, such systems involve several trustworthy challenges such as safety, robustness, and generalization, due to their deployment in open-ended and real-time environments. To evaluate and improve trustworthiness, simulations or so-called digital twins are largely utilized for system development with low cost and high efficiency. One important thing in virtual simulations is scenarios that consist of static and dynamic objects, specific tasks, and evaluation metrics. However, designing diverse, realistic, and effective scenarios is still a challenging problem. One straightforward way is creating scenarios through human design, which is time-consuming and limited by the experience of experts. Another method commonly used in self-driving areas is log replay. This method collects scenario data in the real world and then replays it in simulations or adds random perturbations. Although the replay scenarios are realistic, most of the collected scenarios are redundant since they are all ordinary scenarios that only consider a small portion of critical cases. The desired scenarios should cover all cases in the real world, especially rare but critical events with extremely low probability. Critical scenarios are rare but important to test autonomous systems under risky conditions and unpredictable perturbations, which reveal their trustworthiness.

Learning to View: Decision Transformers for Active Object Detection

Active perception describes a broad class of techniques that couple planning and perception systems to move the robot in a way to give the robot more information about the environment. In most robotic systems, perception is typically independent of motion planning. For example, traditional object detection is passive: it operates only on the images it receives. However, we have a chance to improve the results if we allow planning to consume detection signals and move the robot to collect views that maximize the quality of the results. In this paper, we use reinforcement learning (RL) methods to control the robot in order to obtain images that maximize the detection quality. Specifically, we propose using a Decision Transformer with online fine-tuning, which first optimizes the policy with a pre-collected expert dataset and then improves the learned policy by exploring better solutions in the environment. We evaluate the performance of proposed method on an interactive dataset collected from an indoor scenario simulator. Experimental results demonstrate that our method outperforms all baselines, including expert policy and pure offline RL methods. We also provide exhaustive analyses of the reward distribution and observation space.