Payment channel networks (PCNs) are a layer-2 blockchain scalability solution, with its main entity, the payment channel, enabling transactions between pairs of nodes "off-chain," thus reducing the burden on the layer-1 network. Nodes with multiple channels can serve as relays for multihop payments by providing their liquidity and withholding part of the payment amount as a fee. Relay nodes might after a while end up with one or more unbalanced channels, and thus need to trigger a rebalancing operation. In this paper, we study how a relay node can maximize its profits from fees by using the rebalancing method of submarine swaps. We introduce a stochastic model to capture the dynamics of a relay node observing random transaction arrivals and performing occasional rebalancing operations, and express the system evolution as a Markov Decision Process. We formulate the problem of the maximization of the node's fortune over time over all rebalancing policies, and approximate the optimal solution by designing a Deep Reinforcement Learning (DRL)-based rebalancing policy. We build a discrete event simulator of the system and use it to demonstrate the DRL policy's superior performance under most conditions by conducting a comparative study of different policies and parameterizations. Our work is the first to introduce DRL for liquidity management in the complex world of PCNs.

Contextual batched bandit (CBB) is a setting where a batch of rewards is observed from the environment at the end of each episode, but the rewards of the non-executed actions are unobserved, resulting in partial-information feedback. Existing approaches for CBB often ignore the rewards of the non-executed actions, leading to underutilization of feedback information. In this paper, we propose an efficient approach called Sketched Policy Updating with Imputed Rewards (SPUIR) that completes the unobserved rewards using sketching, which approximates the full-information feedbacks. We formulate reward imputation as an imputation regularized ridge regression problem that captures the feedback mechanisms of both executed and non-executed actions. To reduce time complexity, we solve the regression problem using randomized sketching. We prove that our approach achieves an instantaneous regret with controllable bias and smaller variance than approaches without reward imputation. Furthermore, our approach enjoys a sublinear regret bound against the optimal policy. We also present two extensions, a rate-scheduled version and a version for nonlinear rewards, making our approach more practical. Experimental results show that SPUIR outperforms state-of-the-art baselines on synthetic, public benchmark, and real-world datasets.

This thesis provides an overview of the recent advances in reinforcement learning in pricing and hedging financial instruments, with a primary focus on a detailed explanation of the Q-Learning Black Scholes approach, introduced by Halperin (2017). This reinforcement learning approach bridges the traditional Black and Scholes (1973) model with novel artificial intelligence algorithms, enabling option pricing and hedging in a completely model-free and data-driven way. This paper also explores the algorithm's performance under different state variables and scenarios for a European put option. The results reveal that the model is an accurate estimator under different levels of volatility and hedging frequency. Moreover, this method exhibits robust performance across various levels of option's moneyness. Lastly, the algorithm incorporates proportional transaction costs, indicating diverse impacts on profit and loss, affected by different statistical properties of the state variables.

Nearly all real world tasks are inherently partially observable, necessitating the use of memory in Reinforcement Learning (RL). Most model-free approaches summarize the trajectory into a latent Markov state using memory models borrowed from Supervised Learning (SL), even though RL tends to exhibit different training and efficiency characteristics. Addressing this discrepancy, we introduce Fast and Forgetful Memory, an algorithm-agnostic memory model designed specifically for RL. Our approach constrains the model search space via strong structural priors inspired by computational psychology. It is a drop-in replacement for recurrent neural networks (RNNs) in recurrent RL algorithms, achieving greater reward than RNNs across various recurrent benchmarks and algorithms without changing any hyperparameters. Moreover, Fast and Forgetful Memory exhibits training speeds two orders of magnitude faster than RNNs, attributed to its logarithmic time and linear space complexity. Our implementation is available at https://github.com/proroklab/ffm.

Cooperation is challenging in biological systems, human societies, and multi-agent systems in general. While a group can benefit when everyone cooperates, it is tempting for each agent to act selfishly instead. Prior human studies show that people can overcome such social dilemmas while choosing interaction partners, i.e., strategic network rewiring. However, little is known about how agents, including humans, can learn about cooperation from strategic rewiring and vice versa. Here, we perform multi-agent reinforcement learning simulations in which two agents play the Prisoner's Dilemma game iteratively. Each agent has two policies: one controls whether to cooperate or defect; the other controls whether to rewire connections with another agent. This setting enables us to disentangle complex causal dynamics between cooperation and network rewiring. We find that network rewiring facilitates mutual cooperation even when one agent always offers cooperation, which is vulnerable to free-riding. We then confirm that the network-rewiring effect is exerted through agents' learning of ostracism, that is, connecting to cooperators and disconnecting from defectors. However, we also find that ostracism alone is not sufficient to make cooperation emerge. Instead, ostracism emerges from the learning of cooperation, and existing cooperation is subsequently reinforced due to the presence of ostracism. Our findings provide insights into the conditions and mechanisms necessary for the emergence of cooperation with network rewiring.

We present a universal motion representation that encompasses a comprehensive range of motor skills for physics-based humanoid control. Due to the high-dimensionality of humanoid control as well as the inherent difficulties in reinforcement learning, prior methods have focused on learning skill embeddings for a narrow range of movement styles (e.g. locomotion, game characters) from specialized motion datasets. This limited scope hampers its applicability in complex tasks. Our work closes this gap, significantly increasing the coverage of motion representation space. To achieve this, we first learn a motion imitator that can imitate all of human motion from a large, unstructured motion dataset. We then create our motion representation by distilling skills directly from the imitator. This is achieved using an encoder-decoder structure with a variational information bottleneck. Additionally, we jointly learn a prior conditioned on proprioception (humanoid's own pose and velocities) to improve model expressiveness and sampling efficiency for downstream tasks. Sampling from the prior, we can generate long, stable, and diverse human motions. Using this latent space for hierarchical RL, we show that our policies solve tasks using natural and realistic human behavior. We demonstrate the effectiveness of our motion representation by solving generative tasks (e.g. strike, terrain traversal) and motion tracking using VR controllers.

Offline reinforcement learning (RL) leverages previously collected data to extract policies that return satisfying performance in online environments. However, offline RL suffers from the distribution shift between the offline dataset and the online environment. In the multi-agent RL (MARL) setting, this distribution shift may arise from the nonstationary opponents (exogenous agents beyond control) in the online testing who display distinct behaviors from those recorded in the offline dataset. Hence, the key to the broader deployment of offline MARL is the online adaptation to nonstationary opponents. Recent advances in large language models have demonstrated the surprising generalization ability of the transformer architecture in sequence modeling, which prompts one to wonder \textit{whether the offline-trained transformer policy adapts to nonstationary opponents during online testing}. This work proposes the self-confirming loss (SCL) in offline transformer training to address the online nonstationarity, which is motivated by the self-confirming equilibrium (SCE) in game theory. The gist is that the transformer learns to predict the opponents' future moves based on which it acts accordingly. As a weaker variant of Nash equilibrium (NE), SCE (equivalently, SCL) only requires local consistency: the agent's local observations do not deviate from its conjectures, leading to a more adaptable policy than the one dictated by NE focusing on global optimality. We evaluate the online adaptability of the self-confirming transformer (SCT) by playing against nonstationary opponents employing a variety of policies, from the random one to the benchmark MARL policies. Experimental results demonstrate that SCT can adapt to nonstationary opponents online, achieving higher returns than vanilla transformers and offline MARL baselines.

Designing effective policies for the online 3D bin packing problem (3D-BPP) has been a long-standing challenge, primarily due to the unpredictable nature of incoming box sequences and stringent physical constraints. While current deep reinforcement learning (DRL) methods for online 3D-BPP have shown promising results in optimizing average performance over an underlying box sequence distribution, they often fail in real-world settings where some worst-case scenarios can materialize. Standard robust DRL algorithms tend to overly prioritize optimizing the worst-case performance at the expense of performance under normal problem instance distribution. To address these issues, we first introduce a permutation-based attacker to investigate the practical robustness of both DRL-based and heuristic methods proposed for solving online 3D-BPP. Then, we propose an adjustable robust reinforcement learning (AR2L) framework that allows efficient adjustment of robustness weights to achieve the desired balance of the policy's performance in average and worst-case environments. Specifically, we formulate the objective function as a weighted sum of expected and worst-case returns, and derive the lower performance bound by relating to the return under a mixture dynamics. To realize this lower bound, we adopt an iterative procedure that searches for the associated mixture dynamics and improves the corresponding policy. We integrate this procedure into two popular robust adversarial algorithms to develop the exact and approximate AR2L algorithms. Experiments demonstrate that AR2L is versatile in the sense that it improves policy robustness while maintaining an acceptable level of performance for the nominal case.

A runtime assurance system (RTA) for a given plant enables the exercise of an untrusted or experimental controller while assuring safety with a backup (or safety) controller. The relevant computational design problem is to create a logic that assures safety by switching to the safety controller as needed, while maximizing some performance criteria, such as the utilization of the untrusted controller. Existing RTA design strategies are well-known to be overly conservative and, in principle, can lead to safety violations. In this paper, we formulate the optimal RTA design problem and present a new approach for solving it. Our approach relies on reward shaping and reinforcement learning. It can guarantee safety and leverage machine learning technologies for scalability. We have implemented this algorithm and present experimental results comparing our approach with state-of-the-art reachability and simulation-based RTA approaches in a number of scenarios using aircraft models in 3D space with complex safety requirements. Our approach can guarantee safety while increasing utilization of the experimental controller over existing approaches.

This investigation introduces a novel deep reinforcement learning-based suite to control floating platforms in both simulated and real-world environments. Floating platforms serve as versatile test-beds to emulate microgravity environments on Earth. Our approach addresses the system and environmental uncertainties in controlling such platforms by training policies capable of precise maneuvers amid dynamic and unpredictable conditions. Leveraging state-of-the-art deep reinforcement learning techniques, our suite achieves robustness, adaptability, and good transferability from simulation to reality. Our Deep Reinforcement Learning (DRL) framework provides advantages such as fast training times, large-scale testing capabilities, rich visualization options, and ROS bindings for integration with real-world robotic systems. Beyond policy development, our suite provides a comprehensive platform for researchers, offering open-access at https://github.com/elharirymatteo/RANS/tree/ICRA24.