Developing an automated driving system capable of navigating complex traffic environments remains a formidable challenge. Unlike rule-based or supervised learning-based methods, Deep Reinforcement Learning (DRL) based controllers eliminate the need for domain-specific knowledge and datasets, thus providing adaptability to various scenarios. Nonetheless, a common limitation of existing studies on DRL-based controllers is their focus on driving scenarios with simple traffic patterns, which hinders their capability to effectively handle complex driving environments with delayed, long-term rewards, thus compromising the generalizability of their findings. In response to these limitations, our research introduces a pioneering hierarchical framework that efficiently decomposes intricate decision-making problems into manageable and interpretable subtasks. We adopt a two step training process that trains the high-level controller and low-level controller separately. The high-level controller exhibits an enhanced exploration potential with long-term delayed rewards, and the low-level controller provides longitudinal and lateral control ability using short-term instantaneous rewards. Through simulation experiments, we demonstrate the superiority of our hierarchical controller in managing complex highway driving situations.

Age-of-information (AoI) and transmission power are crucial performance metrics in low energy wireless networks, where information freshness is of paramount importance. This study examines a power-limited internet of things (IoT) network supported by a flying unmanned aerial vehicle(UAV) that collects data. Our aim is to optimize the UAV flight trajectory and scheduling policy to minimize a varying AoI and transmission power combination. To tackle this variation, this paper proposes a meta-deep reinforcement learning (RL) approach that integrates deep Q-networks (DQNs) with model-agnostic meta-learning (MAML). DQNs determine optimal UAV decisions, while MAML enables scalability across varying objective functions. Numerical results indicate that the proposed algorithm converges faster and adapts to new objectives more effectively than traditional deep RL methods, achieving minimal AoI and transmission power overall.

Sparse continuous policies are distributions that can choose some actions at random yet keep strictly zero probability for the other actions, which are radically different from the Gaussian. They have important real-world implications, e.g. in modeling safety-critical tasks like medicine. The combination of offline reinforcement learning and sparse policies provides a novel paradigm that enables learning completely from logged datasets a safety-aware sparse policy. However, sparse policies can cause difficulty with the existing offline algorithms which require evaluating actions that fall outside of the current support. In this paper, we propose the first offline policy optimization algorithm that tackles this challenge: Fat-to-Thin Policy Optimization (FtTPO). Specifically, we maintain a fat (heavy-tailed) proposal policy that effectively learns from the dataset and injects knowledge to a thin (sparse) policy, which is responsible for interacting with the environment. We instantiate FtTPO with the general $q$-Gaussian family that encompasses both heavy-tailed and sparse policies and verify that it performs favorably in a safety-critical treatment simulation and the standard MuJoCo suite. Our code is available at \url{https://github.com/lingweizhu/fat2thin}.

Intelligent decision-making within large and redundant action spaces remains challenging in deep reinforcement learning. Considering similar but ineffective actions at each step can lead to repetitive and unproductive trials. Existing methods attempt to improve agent exploration by reducing or penalizing redundant actions, yet they fail to provide quantitative and reliable evidence to determine redundancy. In this paper, we propose a method to improve exploration efficiency by estimating the causal effects of actions. Unlike prior methods, our approach offers quantitative results regarding the causality of actions for one-step transitions. We first pre-train an inverse dynamics model to serve as prior knowledge of the environment. Subsequently, we classify actions across the entire action space at each time step and estimate the causal effect of each action to suppress redundant actions during exploration. We provide a theoretical analysis to demonstrate the effectiveness of our method and present empirical results from simulations in environments with redundant actions to evaluate its performance. Our implementation is available at https://github.com/agi-brain/cee.git.

This paper addresses the problem of learning programmatic policies, which are structured in programmatic classes such as programming languages or regression trees. To this end, the paper proposes a "lift-and-project" framework (IPPG) that alternatively (1) optimizes a policy parameterized by a neural network in an unconstrained policy space and (2) projects the learned knowledge to space where the desired policy is constrained with a programmatic representation. Specifically, (1) is achieved by using deep policy gradient methods (e.g. DDPG, TRPO, etc.) and (2) is obtained by synthesizing programs to describe behaviors (program synthesis via imitation learning). The experiments on TORCS (a simulated car racing environment) show that the learned programmatic policies outperform the methods that imitate or distill a pre-trained neural policy and DDPG.

While the reviewers generally support acceptance, some concerns remain. We strongly encourage the authors to consider and address the concerns raised by the reviewers, as there remains room for improvement. While the paper is borderline due to these concerns, it falls on the side of acceptance due to the general support and strong support from reviewer 2.

This is a key study in the OPE literature, as methods to provide better stability for off-policy methods are required for practical applications of RL. _x000B_ - Table 1 is useful - provides a good summary and comparison of existing OPE estimators. Section 2.1 further provides a good summary of existing OPE estimators based on consistency, stability and boundedness. This is well written and easy to follow - and useful for the community as it provides a direct comparison between existing OPE estimators in terms of several properties.

This paper presents new estimators for Off Policy Evaluation (OPE) based on likelihoods and argues that the new estimators are better than Importance Sampling (IS). The paper provides strong theoretical guarantees of the estimators, and demonstrates their through simple experiments. The reviewers agree that the paper is well written overall and the proposed methods are technically sound and likely to be built upon by the community. One reviewer is unsure if the proposed methods will be practical in RL applications. The experiments are performed on very simple tasks.

Weaknesses: The main weakness of the method is a reliance on accurate relabelling. The paper argues that actor-critic networks got casually confused due to (almost) disjoint task distributions and then hopes that reward models will not have the same problem. However, it seems that the problem also affects reward models, as a reward ensemble is used in the experiments. There is no ablation study to investigate the necessity of this ensemble in the offline setting. Can you explain why you did not use the setting from 5.1 and 5.2 to evaluate this component of your model?

Reviewers find the paper well-motivated and concisely written. While most of the techniques employed in the paper have been investigated in the literature, the work finds a bag of good tricks to solve the phenomenon the authors observed in multi-task batch RL where agents rely on shortcuts to identify tasks and hence do not generalize. Reviewers would like to see more expansion on related works, and better baselines and experiment environment to strengthen the work. Please try to incorporate these feedback when revising your draft.