Tactics2D is an open-source multi-agent reinforcement learning library with a Python backend. Its goal is to provide a convenient toolset for researchers to develop decision-making algorithms for autonomous driving. The library includes diverse traffic scenarios implemented as gym-based environments equipped with multi-sensory capabilities and violation detection for traffic rules. Additionally, it features a reinforcement learning baseline tested with reasonable evaluation metrics. Tactics2D is highly modular and customizable. The source code of Tactics2D is available at https://github.com/WoodOxen/Tactics2D.
Interpretability in machine learning is critical for the safe deployment of learned policies across legally-regulated and safety-critical domains. While gradient-based approaches in reinforcement learning have achieved tremendous success in learning policies for continuous control problems such as robotics and autonomous driving, the lack of interpretability is a fundamental barrier to adoption. We propose Interpretable Continuous Control Trees (ICCTs), a tree-based model that can be optimized via modern, gradient-based, reinforcement learning approaches to produce high-performing, interpretable policies. The key to our approach is a procedure for allowing direct optimization in a sparse decision-tree-like representation. We validate ICCTs against baselines across six domains, showing that ICCTs are capable of learning policies that parity or outperform baselines by up to 33% in autonomous driving scenarios while achieving a 300x-600x reduction in the number of parameters against deep learning baselines. We prove that ICCTs can serve as universal function approximators and display analytically that ICCTs can be verified in linear time. Furthermore, we deploy ICCTs in two realistic driving domains, based on interstate Highway-94 and 280 in the US. Finally, we verify ICCT's utility with end-users and find that ICCTs are rated easier to simulate, quicker to validate, and more interpretable than neural networks.
Meta reinforcement learning (Meta RL) has been amply explored to quickly learn an unseen task by transferring previously learned knowledge from similar tasks. However, most state-of-the-art algorithms require the meta-training tasks to have a dense coverage on the task distribution and a great amount of data for each of them. In this paper, we propose MetaDreamer, a context-based Meta RL algorithm that requires less real training tasks and data by doing meta-imagination and MDP-imagination. We perform meta-imagination by interpolating on the learned latent context space with disentangled properties, as well as MDP-imagination through the generative world model where physical knowledge is added to plain VAE networks. Our experiments with various benchmarks show that MetaDreamer outperforms existing approaches in data efficiency and interpolated generalization.
Multi-Agent Reinforcement Learning (MARL) has shown promising results across several domains. Despite this promise, MARL policies often lack robustness and are therefore sensitive to small changes in their environment. This presents a serious concern for the real world deployment of MARL algorithms, where the testing environment may slightly differ from the training environment. In this work we show that we can gain robustness by controlling a policy's Lipschitz constant, and under mild conditions, establish the existence of a Lipschitz and close-to-optimal policy. Based on these insights, we propose a new robust MARL framework, ERNIE, that promotes the Lipschitz continuity of the policies with respect to the state observations and actions by adversarial regularization. The ERNIE framework provides robustness against noisy observations, changing transition dynamics, and malicious actions of agents. However, ERNIE's adversarial regularization may introduce some training instability. To reduce this instability, we reformulate adversarial regularization as a Stackelberg game. We demonstrate the effectiveness of the proposed framework with extensive experiments in traffic light control and particle environments. In addition, we extend ERNIE to mean-field MARL with a formulation based on distributionally robust optimization that outperforms its non-robust counterpart and is of independent interest. Our code is available at https://github.com/abukharin3/ERNIE.
As neural networks become more integrated into the systems that we depend on for transportation, medicine, and security, it becomes increasingly important that we develop methods to analyze their behavior to ensure that they are safe to use within these contexts. The methods used in this paper seek to certify safety for closed-loop systems with neural network controllers, i.e., neural feedback loops, using backward reachability analysis. Namely, we calculate backprojection (BP) set over-approximations (BPOAs), i.e., sets of states that lead to a given target set that bounds dangerous regions of the state space. The system's safety can then be certified by checking its current state against the BPOAs. While over-approximating BPs is significantly faster than calculating exact BP sets, solving the relaxed problem leads to conservativeness. To combat conservativeness, partitioning strategies can be used to split the problem into a set of sub-problems, each less conservative than the unpartitioned problem. We introduce a hybrid partitioning method that uses both target set partitioning (TSP) and backreachable set partitioning (BRSP) to overcome a lower bound on estimation error that is present when using BRSP. Numerical results demonstrate a near order-of-magnitude reduction in estimation error compared to BRSP or TSP given the same computation time.
The field of Meta Reinforcement Learning (Meta-RL) has seen substantial advancements recently. In particular, off-policy methods were developed to improve the data efficiency of Meta-RL techniques. \textit{Probabilistic embeddings for actor-critic RL} (PEARL) is currently one of the leading approaches for multi-MDP adaptation problems. A major drawback of many existing Meta-RL methods, including PEARL, is that they do not explicitly consider the safety of the prior policy when it is exposed to a new task for the very first time. This is very important for some real-world applications, including field robots and Autonomous Vehicles (AVs). In this paper, we develop the PEARL PLUS (PEARL$^+$) algorithm, which optimizes the policy for both prior safety and posterior adaptation. Building on top of PEARL, our proposed PEARL$^+$ algorithm introduces a prior regularization term in the reward function and a new Q-network for recovering the state-action value with prior context assumption, to improve the robustness and safety of the trained network exposing to a new task for the first time. The performance of the PEARL$^+$ method is demonstrated by solving three safety-critical decision-making problems related to robots and AVs, including two MuJoCo benchmark problems. From the simulation experiments, we show that the safety of the prior policy is significantly improved compared to that of the original PEARL method.
It is essential for an automated vehicle in the field to perform discretionary lane changes with appropriate roadmanship - driving safely and efficiently without annoying or endangering other road users - under a wide range of traffic cultures and driving conditions. While deep reinforcement learning methods have excelled in recent years and been applied to automated vehicle driving policy, there are concerns about their capability to quickly adapt to unseen traffic with new environment dynamics. We formulate this challenge as a multi-Markov Decision Processes (MDPs) adaptation problem and developed Meta Reinforcement Learning (MRL) driving policies to showcase their quick learning capability. Two types of distribution variation in environments were designed and simulated to validate the fast adaptation capability of resulting MRL driving policies which significantly outperform a baseline RL.
This paper proposes a method to extract the position and pose of vehicles in the 3D world from a single traffic camera. Most previous monocular 3D vehicle detection algorithms focused on cameras on vehicles from the perspective of a driver, and assumed known intrinsic and extrinsic calibration. On the contrary, this paper focuses on the same task using uncalibrated monocular traffic cameras. We observe that the homography between the road plane and the image plane is essential to 3D vehicle detection and the data synthesis for this task, and the homography can be estimated without the camera intrinsics and extrinsics. We conduct 3D vehicle detection by estimating the rotated bounding boxes (r-boxes) in the bird's eye view (BEV) images generated from inverse perspective mapping. We propose a new regression target called \textit{tailed~r-box} and a \textit{dual-view} network architecture which boosts the detection accuracy on warped BEV images. Experiments show that the proposed method can generalize to new camera and environment setups despite not seeing imaged from them during training.
It is important to build a rigorous verification and validation (V&V) process to evaluate the safety of highly automated vehicles (HAVs) before their wide deployment on public roads. In this paper, we propose an interaction-aware framework for HAV safety evaluation which is suitable for some highly-interactive driving scenarios including highway merging, roundabout entering, etc. Contrary to existing approaches where the primary other vehicle (POV) takes predetermined maneuvers, we model the POV as a game-theoretic agent. To capture a wide variety of interactions between the POV and the vehicle under test (VUT), we characterize the interactive behavior using level-k game theory and social value orientation and train a diverse set of POVs using reinforcement learning. Moreover, we propose an adaptive test case sampling scheme based on the Gaussian process regression technique to generate customized and diverse challenging cases. The highway merging is used as the example scenario. We found the proposed method is able to capture a wide range of POV behaviors and achieve better coverage of the failure modes of the VUT compared with other evaluation approaches.
Safeguard functions such as those provided by advanced emergency braking (AEB) can provide another layer of safety for autonomous vehicles (AV). A smart safeguard function should adapt the activation conditions to the driving policy, to avoid unnecessary interventions as well as improve vehicle safety. This paper proposes a driving-policy adaptive safeguard (DPAS) design, including a collision avoidance strategy and an activation function. The collision avoidance strategy is designed in a reinforcement learning framework, obtained by Monte-Carlo Tree Search (MCTS). It can learn from past collisions and manipulate both braking and steering in stochastic traffics. The driving-policy adaptive activation function should dynamically assess current driving policy risk and kick in when an urgent threat is detected. To generate this activation function, MCTS' exploration and rollout modules are designed to fully evaluate the AV's current driving policy, and then explore other safer actions. In this study, the DPAS is validated with two typical highway-driving policies. The results are obtained through and 90,000 times in the stochastic and aggressive simulated traffic. The results are calibrated by naturalistic driving data and show that the proposed safeguard reduces the collision rate significantly without introducing more interventions, compared with the state-based benchmark safeguards. In summary, the proposed safeguard leverages the learning-based method in stochastic and emergent scenarios and imposes minimal influence on the driving policy.