In many branches of engineering, Banach contraction mapping theorem is employed to establish the convergence of certain deterministic algorithms. Randomized versions of these algorithms have been developed that have proved useful in data-driven problems. In a class of randomized algorithms, in each iteration, the contraction map is approximated with an operator that uses independent and identically distributed samples of certain random variables. This leads to iterated random operators acting on an initial point in a complete metric space, and it generates a Markov chain. In this paper, we develop a new stochastic dominance based proof technique, called probabilistic contraction analysis, for establishing the convergence in probability of Markov chains generated by such iterated random operators in certain limiting regime. The methods developed in this paper provides a general framework for understanding convergence of a wide variety of Monte Carlo methods in which contractive property is present. We apply the convergence result to conclude the convergence of fitted value iteration and fitted relative value iteration in continuous state and continuous action Markov decision problems as representative applications of the general framework developed here.

Reinforcement learning is a powerful technique for learning from trial and error, but it often requires a large number of interactions to achieve good performance. In some domains, such as sparse-reward tasks, an oracle that can provide useful feedback or guidance to the agent during the learning process is really of great importance. However, querying the oracle too frequently may be costly or impractical, and the oracle may not always have a clear answer for every situation. Therefore, we propose a novel method for interacting with the oracle in a selective and efficient way, using a retrieval-based approach. We assume that the interaction can be modeled as a sequence of templated questions and answers, and that there is a large corpus of previous interactions available. We use a neural network to encode the current state of the agent and the oracle, and retrieve the most relevant question from the corpus to ask the oracle. We then use the oracle's answer to update the agent's policy and value function. We evaluate our method on an object manipulation task. We show that our method can significantly improve the efficiency of RL by reducing the number of interactions needed to reach a certain level of performance, compared to baselines that do not use the oracle or use it in a naive way.

Hierarchical reinforcement learning has been a compelling approach for achieving goal directed behavior over long sequences of actions. However, it has been challenging to implement in realistic or open-ended environments. A main challenge has been to find the right space of sub-goals over which to instantiate a hierarchy. We present a novel approach where we use data from humans solving these tasks to softly supervise the goal space for a set of long range tasks in a 3D embodied environment. In particular, we use unconstrained natural language to parameterize this space. This has two advantages: first, it is easy to generate this data from naive human participants; second, it is flexible enough to represent a vast range of sub-goals in human-relevant tasks. Our approach outperforms agents that clone expert behavior on these tasks, as well as HRL from scratch without this supervised sub-goal space. Our work presents a novel approach to combining human expert supervision with the benefits and flexibility of reinforcement learning.

The application of artificial intelligence to simulate air-to-air combat scenarios is attracting increasing attention. To date the high-dimensional state and action spaces, the high complexity of situation information (such as imperfect and filtered information, stochasticity, incomplete knowledge about mission targets) and the nonlinear flight dynamics pose significant challenges for accurate air combat decision-making. These challenges are exacerbated when multiple heterogeneous agents are involved. We propose a hierarchical multi-agent reinforcement learning framework for air-to-air combat with multiple heterogeneous agents. In our framework, the decision-making process is divided into two stages of abstraction, where heterogeneous low-level policies control the action of individual units, and a high-level commander policy issues macro commands given the overall mission targets. Low-level policies are trained for accurate unit combat control. Their training is organized in a learning curriculum with increasingly complex training scenarios and league-based self-play. The commander policy is trained on mission targets given pre-trained low-level policies. The empirical validation advocates the advantages of our design choices.

Delays are inherent to most dynamical systems. Besides shifting the process in time, they can significantly affect their performance. For this reason, it is usually valuable to study the delay and account for it. Because they are dynamical systems, it is of no surprise that sequential decision-making problems such as Markov decision processes (MDP) can also be affected by delays. These processes are the foundational framework of reinforcement learning (RL), a paradigm whose goal is to create artificial agents capable of learning to maximise their utility by interacting with their environment. RL has achieved strong, sometimes astonishing, empirical results, but delays are seldom explicitly accounted for. The understanding of the impact of delay on the MDP is limited. In this dissertation, we propose to study the delay in the agent's observation of the state of the environment or in the execution of the agent's actions. We will repeatedly change our point of view on the problem to reveal some of its structure and peculiarities. A wide spectrum of delays will be considered, and potential solutions will be presented. This dissertation also aims to draw links between celebrated frameworks of the RL literature and the one of delays.

This paper addresses the prediction stability, prediction accuracy and control capability of the current probabilistic model-based reinforcement learning (MBRL) built on neural networks. A novel approach dropout-based probabilistic ensembles with trajectory sampling (DPETS) is proposed where the system uncertainty is stably predicted by combining the Monte-Carlo dropout and trajectory sampling in one framework. Its loss function is designed to correct the fitting error of neural networks for more accurate prediction of probabilistic models. The state propagation in its policy is extended to filter the aleatoric uncertainty for superior control capability. Evaluated by several Mujoco benchmark control tasks under additional disturbances and one practical robot arm manipulation task, DPETS outperforms related MBRL approaches in both average return and convergence velocity while achieving superior performance than well-known model-free baselines with significant sample efficiency. The open source code of DPETS is available at https://github.com/mrjun123/DPETS.

Sensing and communication technologies have enhanced learning-based decision making methodologies for multi-agent systems such as connected autonomous vehicles (CAV). However, most existing safe reinforcement learning based methods assume accurate state information. It remains challenging to achieve safety requirement under state uncertainties for CAVs, considering the noisy sensor measurements and the vulnerability of communication channels. In this work, we propose a Robust Multi-Agent Proximal Policy Optimization with robust Safety Shield (SR-MAPPO) for CAVs in various driving scenarios. Both robust MARL algorithm and control barrier function (CBF)-based safety shield are used in our approach to cope with the perturbed or uncertain state inputs. The robust policy is trained with a worst-case Q function regularization module that pursues higher lower-bounded reward in the former, whereas the latter, i.e., the robust CBF safety shield accounts for CAVs' collision-free constraints in complicated driving scenarios with even perturbed vehicle state information. We validate the advantages of SR-MAPPO in robustness and safety and compare it with baselines under different driving and state perturbation scenarios in CARLA simulator. The SR-MAPPO policy is verified to maintain higher safety rates and efficiency (reward) when threatened by both state perturbations and unconnected vehicles' dangerous behaviors.

Differentiable quantum architecture search (DQAS) is a gradient-based framework to design quantum circuits automatically in the NISQ era. It was motivated by such as low fidelity of quantum hardware, low flexibility of circuit architecture, high circuit design cost, barren plateau (BP) problem, and periodicity of weights. People used it to address error mitigation, unitary decomposition, and quantum approximation optimization problems based on fixed datasets. Quantum reinforcement learning (QRL) is a part of quantum machine learning and often has various data. QRL usually uses a manually designed circuit. However, the pre-defined circuit needs more flexibility for different tasks, and the circuit design based on various datasets could become intractable in the case of a large circuit. The problem of whether DQAS can be applied to quantum deep Q-learning with various datasets is still open. The main target of this work is to discover the capability of DQAS to solve quantum deep Q-learning problems. We apply a gradient-based framework DQAS on reinforcement learning tasks and evaluate it in two different environments - cart pole and frozen lake. It contains input- and output weights, progressive search, and other new features. The experiments conclude that DQAS can design quantum circuits automatically and efficiently. The evaluation results show significant outperformance compared to the manually designed circuit. Furthermore, the performance of the automatically created circuit depends on whether the super-circuit learned well during the training process. This work is the first to show that gradient-based quantum architecture search is applicable to QRL tasks.

In Reinforcement Learning, the trade-off between exploration and exploitation poses a complex challenge for achieving efficient learning from limited samples. While recent works have been effective in leveraging past experiences for policy updates, they often overlook the potential of reusing past experiences for data collection. Independent of the underlying RL algorithm, we introduce the concept of a Contrastive Initial State Buffer, which strategically selects states from past experiences and uses them to initialize the agent in the environment in order to guide it toward more informative states. We validate our approach on two complex robotic tasks without relying on any prior information about the environment: (i) locomotion of a quadruped robot traversing challenging terrains and (ii) a quadcopter drone racing through a track. The experimental results show that our initial state buffer achieves higher task performance than the nominal baseline while also speeding up training convergence.

The idea of decision-aware model learning, that models should be accurate where it matters for decision-making, has gained prominence in model-based reinforcement learning. While promising theoretical results have been established, the empirical performance of algorithms leveraging a decision-aware loss has been lacking, especially in continuous control problems. In this paper, we present a study on the necessary components for decision-aware reinforcement learning models and we showcase design choices that enable well-performing algorithms. To this end, we provide a theoretical and empirical investigation into prominent algorithmic ideas in the field. We highlight that empirical design decisions established in the MuZero line of works are vital to achieving good performance for related algorithms, and we showcase differences in behavior between different instantiations of value-aware algorithms in stochastic environments. Using these insights, we propose the Latent Model-Based Decision-Aware Actor-Critic framework ($\lambda$-AC) for decision-aware model-based reinforcement learning in continuous state-spaces and highlight important design choices in different environments.