The stochastic control problem of optimal market making is among the central problems in quantitative finance. In this paper, a deep reinforcement learning-based controller is trained on a weakly consistent, multivariate Hawkes process-based limit order book simulator to obtain market making controls. The proposed approach leverages the advantages of Monte Carlo backtesting and contributes to the line of research on market making under weakly consistent limit order book models. The ensuing deep reinforcement learning controller is compared to multiple market making benchmarks, with the results indicating its superior performance with respect to various risk-reward metrics, even under significant transaction costs.

We present a novel Learning from Demonstration (LfD) method, Deformable Manipulation from Demonstrations (DMfD), to solve deformable manipulation tasks using states or images as inputs, given expert demonstrations. Our method uses demonstrations in three different ways, and balances the trade-off between exploring the environment online and using guidance from experts to explore high dimensional spaces effectively. We test DMfD on a set of representative manipulation tasks for a 1-dimensional rope and a 2-dimensional cloth from the SoftGym suite of tasks, each with state and image observations. Our method exceeds baseline performance by up to 12.9% for state-based tasks and up to 33.44% on image-based tasks, with comparable or better robustness to randomness. Additionally, we create two challenging environments for folding a 2D cloth using image-based observations, and set a performance benchmark for them. We deploy DMfD on a real robot with a minimal loss in normalized performance during real-world execution compared to simulation (~6%). Source code is on github.com/uscresl/dmfd

Reinforcement learning allows an agent to decide its next action based on its current state by learning behaviours that will maximise a reward.

One of the biggest barriers to traditional machine learning is that most supervised and unsupervised machine learning algorithms need huge amounts of data to be useful in real world use cases. Even then, the AI is unable to learn as it goes without human supervision and feedback. What if an AI could learn from scratch? As one of the most famous examples, Google's DeepMind built AlphaGo, which was able to beat the best Go player in history, Lee Sedol. To learn optimal strategies, it used a combination of deep learning and reinforcement learning -- as in, by playing hundreds of thousands of Go games against itself.

Data-driven model predictive control has two key advantages over model-free methods: a potential for improved sample efficiency through model learning, and better performance as computational budget for planning increases. However, it is both costly to plan over long horizons and challenging to obtain an accurate model of the environment. In this work, we combine the strengths of model-free and model-based methods. We use a learned task-oriented latent dynamics model for local trajectory optimization over a short horizon, and use a learned terminal value function to estimate long-term return, both of which are learned jointly by temporal difference learning. Our method, TD-MPC, achieves superior sample efficiency and asymptotic performance over prior work on both state and image-based continuous control tasks from DMControl and Meta-World. Code and video results are available at https://nicklashansen.github.io/td-mpc.

We consider an improper reinforcement learning setting where a learner is given $M$ base controllers for an unknown Markov decision process, and wishes to combine them optimally to produce a potentially new controller that can outperform each of the base ones. This can be useful in tuning across controllers, learnt possibly in mismatched or simulated environments, to obtain a good controller for a given target environment with relatively few trials. Towards this, we propose two algorithms: (1) a Policy Gradient-based approach; and (2) an algorithm that can switch between a simple Actor-Critic (AC) based scheme and a Natural Actor-Critic (NAC) scheme depending on the available information. Both algorithms operate over a class of improper mixtures of the given controllers. For the first case, we derive convergence rate guarantees assuming access to a gradient oracle. For the AC-based approach we provide convergence rate guarantees to a stationary point in the basic AC case and to a global optimum in the NAC case. Numerical results on (i) the standard control theoretic benchmark of stabilizing an cartpole; and (ii) a constrained queueing task show that our improper policy optimization algorithm can stabilize the system even when the base policies at its disposal are unstable.

We approach the problem of learning by watching humans in the wild. While traditional approaches in Imitation and Reinforcement Learning are promising for learning in the real world, they are either sample inefficient or are constrained to lab settings. Meanwhile, there has been a lot of success in processing passive, unstructured human data. We propose tackling this problem via an efficient one-shot robot learning algorithm, centered around learning from a third-person perspective. We call our method WHIRL: In-the-Wild Human Imitating Robot Learning. WHIRL extracts a prior over the intent of the human demonstrator, using it to initialize our agent's policy. We introduce an efficient real-world policy learning scheme that improves using interactions. Our key contributions are a simple sampling-based policy optimization approach, a novel objective function for aligning human and robot videos as well as an exploration method to boost sample efficiency. We show one-shot generalization and success in real-world settings, including 20 different manipulation tasks in the wild. Videos and talk at https://human2robot.github.io

Reinforcement learning (RL) offers the potential for training generally capable agents that can interact autonomously in the real world. However, one key limitation is the brittleness of RL algorithms to core hyperparameters and network architecture choice. Furthermore, non-stationarities such as evolving training data and increased agent complexity mean that different hyperparameters and architectures may be optimal at different points of training. This motivates AutoRL, a class of methods seeking to automate these design choices. One prominent class of AutoRL methods is Population-Based Training (PBT), which have led to impressive performance in several large scale settings. In this paper, we introduce two new innovations in PBT-style methods. First, we employ trust-region based Bayesian Optimization, enabling full coverage of the high-dimensional mixed hyperparameter search space. Second, we show that using a generational approach, we can also learn both architectures and hyperparameters jointly on-the-fly in a single training run. Leveraging the new highly parallelizable Brax physics engine, we show that these innovations lead to large performance gains, significantly outperforming the tuned baseline while learning entire configurations on the fly. Code is available at https://github.com/xingchenwan/bgpbt.

Although Deep Reinforcement Learning (DRL) has been popular in many disciplines including robotics, state-of-the-art DRL algorithms still struggle to learn long-horizon, multi-step and sparse reward tasks, such as stacking several blocks given only a task-completion reward signal. To improve learning efficiency for such tasks, this paper proposes a DRL exploration technique, termed A^2, which integrates two components inspired by human experiences: Abstract demonstrations and Adaptive exploration. A^2 starts by decomposing a complex task into subtasks, and then provides the correct orders of subtasks to learn. During training, the agent explores the environment adaptively, acting more deterministically for well-mastered subtasks and more stochastically for ill-learnt subtasks. Ablation and comparative experiments are conducted on several grid-world tasks and three robotic manipulation tasks. We demonstrate that A^2 can aid popular DRL algorithms (DQN, DDPG, and SAC) to learn more efficiently and stably in these environments.

We consider some classical optimization problems in path planning and network transport, and we introduce new auction-based algorithms for their optimal and suboptimal solution. The algorithms are based on mathematical ideas that are related to competitive bidding by persons for objects and the attendant market equilibrium, which underlie auction processes. However, the starting point of our algorithms is different, namely weighted and unweighted path construction in directed graphs, rather than assignment of persons to objects. The new algorithms have several potential advantages over existing methods: they are empirically faster in some important contexts, such as max-flow, they are well-suited for on-line replanning, and they can be adapted to distributed asynchronous operation. Moreover, they allow arbitrary initial prices, without complementary slackness restrictions, and thus are better-suited to take advantage of reinforcement learning methods that use off-line training with data, as well as on-line training during real-time operation. The new algorithms may also find use in reinforcement learning contexts involving approximation, such as multistep lookahead and tree search schemes, and/or rollout algorithms.