Recently, sequence learning methods have been applied to the problem of off-policy Reinforcement Learning, including the seminal work on Decision Transformers, which employs transformers for this task. Since transformers are parameter-heavy, cannot benefit from history longer than a fixed window size, and are not computed using recurrence, we set out to investigate the suitability of the S4 family of models, which are based on state-space layers and have been shown to outperform transformers, especially in modeling long-range dependencies. In this work we present two main algorithms: (i) an off-policy training procedure that works with trajectories, while still maintaining the training efficiency of the S4 model. Our results indicate that our method outperforms multiple variants of decision transformers, as well as the other baseline methods on most tasks, while reducing the latency, number of parameters, and training time by several orders of magnitude, making our approach more suitable for real-world RL. Robots are naturally described as being in an observable state, having a multi-dimensional action space and striving to achieve a measurable goal. The complexity of these three elements, and the often non-differentiable links between them, such as the shift between the states given the action and the shift between the states and the reward (with the latter computed based on additional entities), make the use of Reinforcement Learning (RL) natural, see also (Kober et al., 2013; Ibarz et al., 2021). Off-policy RL has preferable sample complexity and is widely used in robotics research, e.g., (Haarnoja et al., 2018; Gu et al., 2017). However, with the advent of accessible physical simulations for generating data, learning complex tasks without a successful sample model is readily approached by on-policy methods Siekmann et al. (2021) and the same holds for the task of adversarial imitation learning Peng et al. (2021; 2022). The decision transformer of Chen et al. (2021) is a sequence-based off-policy RL method that considers sequences of tuples of the form (reward, state, action). Using the auto-regressive capability of transformers, it generates the next action given the desired reward and the current state. The major disadvantages of the decision transformer are the size of the architecture, which is a known limitation in these models, the inference runtime, which stems from the inability to compute the transformer recursively, and the fixed window size, which eliminates long-range dependencies. In this work, we propose a novel, sequence-based RL method that is far more efficient than the decision transformer and more suitable for capturing long-range effects. The method is based on the S4 sequence model, which was designed by Gu et al. (2021a). These authors contributed equally to this work.

Multi-vehicle pursuit (MVP) such as autonomous police vehicles pursuing suspects is important but very challenging due to its mission and safety critical nature. While multi-agent reinforcement learning (MARL) algorithms have been proposed for MVP problem in structured grid-pattern roads, the existing algorithms use randomly training samples in centralized learning, which leads to homogeneous agents showing low collaboration performance. For the more challenging problem of pursuing multiple evading vehicles, these algorithms typically select a fixed target evading vehicle for pursuing vehicles without considering dynamic traffic situation, which significantly reduces pursuing success rate. To address the above problems, this paper proposes a Progression Cognition Reinforcement Learning with Prioritized Experience for MVP (PEPCRL-MVP) in urban multi-intersection dynamic traffic scenes. PEPCRL-MVP uses a prioritization network to assess the transitions in the global experience replay buffer according to the parameters of each MARL agent. With the personalized and prioritized experience set selected via the prioritization network, diversity is introduced to the learning process of MARL, which can improve collaboration and task related performance. Furthermore, PEPCRL-MVP employs an attention module to extract critical features from complex urban traffic environments. These features are used to develop progression cognition method to adaptively group pursuing vehicles. Each group efficiently target one evading vehicle in dynamic driving environments. Extensive experiments conducted with a simulator over unstructured roads of an urban area show that PEPCRL-MVP is superior to other state-of-the-art methods. Specifically, PEPCRL-MVP improves pursuing efficiency by 3.95% over TD3-DMAP and its success rate is 34.78% higher than that of MADDPG. Codes are open sourced.

Variances in ad impression outcomes across demographic groups are increasingly considered to be potentially indicative of algorithmic bias in personalized ads systems. While there are many definitions of fairness that could be applicable in the context of personalized systems, we present a framework which we call the Variance Reduction System (VRS) for achieving more equitable outcomes in Meta's ads systems. VRS seeks to achieve a distribution of impressions with respect to selected protected class (PC) attributes that more closely aligns the demographics of an ad's eligible audience (a function of advertiser targeting criteria) with the audience who sees that ad, in a privacy-preserving manner. We first define metrics to quantify fairness gaps in terms of ad impression variances with respect to PC attributes including gender and estimated race. We then present the VRS for re-ranking ads in an impression variance-aware manner. We evaluate VRS via extensive simulations over different parameter choices and study the effect of the VRS on the chosen fairness metric. We finally present online A/B testing results from applying VRS to Meta's ads systems, concluding with a discussion of future work. We have deployed the VRS to all users in the US for housing ads, resulting in significant improvement in our fairness metric. VRS is the first large-scale deployed framework for pursuing fairness for multiple PC attributes in online advertising.

While reinforcement learning (RL) has achieved great success in acquiring complex skills solely from environmental interactions, it assumes that resets to the initial state are readily available at the end of each episode. Such an assumption hinders the autonomous learning of embodied agents due to the time-consuming and cumbersome workarounds for resetting in the physical world. Hence, there has been a growing interest in autonomous RL (ARL) methods that are capable of learning from non-episodic interactions. However, existing works on ARL are limited by their reliance on prior data and are unable to learn in environments where task-relevant interactions are sparse. In contrast, we propose a demonstration-free ARL algorithm via Implicit and Bi-directional Curriculum (IBC). With an auxiliary agent that is conditionally activated upon learning progress and a bidirectional goal curriculum based on optimal transport, our method outperforms previous methods, even the ones that leverage demonstrations.

The proximal policy optimization (PPO) algorithm stands as one of the most prosperous methods in the field of reinforcement learning (RL). Despite its success, the theoretical understanding of PPO remains deficient. Specifically, it is unclear whether PPO or its optimistic variants can effectively solve linear Markov decision processes (MDPs), which are arguably the simplest models in RL with function approximation. To bridge this gap, we propose an optimistic variant of PPO for episodic adversarial linear MDPs with full-information feedback, and establish a $\tilde{\mathcal{O}}(d^{3/4}H^2K^{3/4})$ regret for it. Here $d$ is the ambient dimension of linear MDPs, $H$ is the length of each episode, and $K$ is the number of episodes. Compared with existing policy-based algorithms, we achieve the state-of-the-art regret bound in both stochastic linear MDPs and adversarial linear MDPs with full information. Additionally, our algorithm design features a novel multi-batched updating mechanism and the theoretical analysis utilizes a new covering number argument of value and policy classes, which might be of independent interest.

In this paper, we investigate a novel safe reinforcement learning problem with step-wise violation constraints. Our problem differs from existing works in that we consider stricter step-wise violation constraints and do not assume the existence of safe actions, making our formulation more suitable for safety-critical applications which need to ensure safety in all decision steps and may not always possess safe actions, e.g., robot control and autonomous driving. We propose a novel algorithm SUCBVI, which guarantees $\widetilde{O}(\sqrt{ST})$ step-wise violation and $\widetilde{O}(\sqrt{H^3SAT})$ regret. Lower bounds are provided to validate the optimality in both violation and regret performance with respect to $S$ and $T$. Moreover, we further study a novel safe reward-free exploration problem with step-wise violation constraints. For this problem, we design an $(\varepsilon,\delta)$-PAC algorithm SRF-UCRL, which achieves nearly state-of-the-art sample complexity $\widetilde{O}((\frac{S^2AH^2}{\varepsilon}+\frac{H^4SA}{\varepsilon^2})(\log(\frac{1}{\delta})+S))$, and guarantees $\widetilde{O}(\sqrt{ST})$ violation during the exploration. The experimental results demonstrate the superiority of our algorithms in safety performance, and corroborate our theoretical results.

Compositional reinforcement learning is a promising approach for training policies to perform complex long-horizon tasks. Typically, a high-level task is decomposed into a sequence of subtasks and a separate policy is trained to perform each subtask. In this paper, we focus on the problem of training subtask policies in a way that they can be used to perform any task; here, a task is given by a sequence of subtasks. We aim to maximize the worst-case performance over all tasks as opposed to the average-case performance. We formulate the problem as a two agent zero-sum game in which the adversary picks the sequence of subtasks. We propose two RL algorithms to solve this game: one is an adaptation of existing multi-agent RL algorithms to our setting and the other is an asynchronous version which enables parallel training of subtask policies. We evaluate our approach on two multi-task environments with continuous states and actions and demonstrate that our algorithms outperform state-of-the-art baselines.

Autonomous vehicles are suited for continuous area patrolling problems. However, finding an optimal patrolling strategy can be challenging for many reasons. Firstly, patrolling environments are often complex and can include unknown environmental factors, such as wind or landscape. Secondly, autonomous vehicles can have failures or hardware constraints, such as limited battery life. Importantly, patrolling large areas often requires multiple agents that need to collectively coordinate their actions. In this work, we consider these limitations and propose an approach based on model-free, deep multi-agent reinforcement learning. In this approach, the agents are trained to patrol an environment with various unknown dynamics and factors. They can automatically recharge themselves to support continuous collective patrolling. A distributed homogeneous multi-agent architecture is proposed, where all patrolling agents execute identical policies locally based on their local observations and shared location information. This architecture provides a patrolling system that can tolerate agent failures and allow supplementary agents to be added to replace failed agents or to increase the overall patrol performance. The solution is validated through simulation experiments from multiple perspectives, including the overall patrol performance, the efficiency of battery recharging strategies, the overall fault tolerance, and the ability to cooperate with supplementary agents.

Despite the promising results achieved, state-of-the-art interactive reinforcement learning schemes rely on passively receiving supervision signals from advisor experts, in the form of either continuous monitoring or pre-defined rules, which inevitably result in a cumbersome and expensive learning process. In this paper, we introduce a novel initiative advisor-in-the-loop actor-critic framework, termed as Ask-AC, that replaces the unilateral advisor-guidance mechanism with a bidirectional learner-initiative one, and thereby enables a customized and efficacious message exchange between learner and advisor. At the heart of Ask-AC are two complementary components, namely action requester and adaptive state selector, that can be readily incorporated into various discrete actor-critic architectures. The former component allows the agent to initiatively seek advisor intervention in the presence of uncertain states, while the latter identifies the unstable states potentially missed by the former especially when environment changes, and then learns to promote the ask action on such states. Experimental results on both stationary and non-stationary environments and across different actor-critic backbones demonstrate that the proposed framework significantly improves the learning efficiency of the agent, and achieves the performances on par with those obtained by continuous advisor monitoring.

Model predictive control (MPC) is a popular approach for trajectory optimization in practical robotics applications. MPC policies can optimize trajectory parameters under kinodynamic and safety constraints and provide guarantees on safety, optimality, generalizability, interpretability, and explainability. However, some behaviors are complex and it is difficult to hand-craft an MPC objective function. A special class of MPC policies called Learnable-MPC addresses this difficulty using imitation learning from expert demonstrations. However, they require the demonstrator and the imitator agents to be identical which is hard to satisfy in many real world applications of robotics. In this paper, we address the practical problem of training Learnable-MPC policies when the demonstrator and the imitator do not share the same dynamics and their state spaces may have a partial overlap. We propose a novel approach that uses a generative adversarial network (GAN) to minimize the Jensen-Shannon divergence between the state-trajectory distributions of the demonstrator and the imitator. We evaluate our approach on a variety of simulated robotics tasks of DeepMind Control suite and demonstrate the efficacy of our approach at learning the demonstrator's behavior without having to copy their actions.