Reinforcement learning (RL) is gaining attention by more and more researchers in quantitative finance as the agent-environment interaction framework is aligned with decision making process in many business problems. Most of the current financial applications using RL algorithms are based on model-free method, which still faces stability and adaptivity challenges. As lots of cutting-edge model-based reinforcement learning (MBRL) algorithms mature in applications such as video games or robotics, we design a new approach that leverages resistance and support (RS) level as regularization terms for action in MBRL, to improve the algorithm's efficiency and stability. From the experiment results, we can see RS level, as a market timing technique, enhances the performance of pure MBRL models in terms of various measurements and obtains better profit gain with less riskiness. Besides, our proposed method even resists big drop (less maximum drawdown) during COVID-19 pandemic period when the financial market got unpredictable crisis. Explanations on why control of resistance and support level can boost MBRL is also investigated through numerical experiments, such as loss of actor-critic network and prediction error of the transition dynamical model. It shows that RS indicators indeed help the MBRL algorithms to converge faster at early stage and obtain smaller critic loss as training episodes increase.
Recent Multi-Agent Reinforcement Learning (MARL) literature has been largely focused on Centralized Training with Decentralized Execution (CTDE) paradigm. CTDE has been a dominant approach for both cooperative and mixed environments due to its capability to efficiently train decentralized policies. While in mixed environments full autonomy of the agents can be a desirable outcome, cooperative environments allow agents to share information to facilitate coordination. Approaches that leverage this technique are usually referred as communication methods, as full autonomy of agents is compromised for better performance. Although communication approaches have shown impressive results, they do not fully leverage this additional information during training phase. In this paper, we propose a new method called MAMBA which utilizes Model-Based Reinforcement Learning (MBRL) to further leverage centralized training in cooperative environments. We argue that communication between agents is enough to sustain a world model for each agent during execution phase while imaginary rollouts can be used for training, removing the necessity to interact with the environment. These properties yield sample efficient algorithm that can scale gracefully with the number of agents. We empirically confirm that MAMBA achieves good performance while reducing the number of interactions with the environment up to an orders of magnitude compared to Model-Free state-of-the-art approaches in challenging domains of SMAC and Flatland.
A crucial challenge in reinforcement learning is to reduce the number of interactions with the environment that an agent requires to master a given task. Transfer learning proposes to address this issue by re-using knowledge from previously learned tasks. However, determining which source task qualifies as the most appropriate for knowledge extraction, as well as the choice regarding which algorithm components to transfer, represent severe obstacles to its application in reinforcement learning. The goal of this paper is to address these issues with modular multi-source transfer learning techniques. The proposed techniques automatically learn how to extract useful information from source tasks, regardless of the difference in state-action space and reward function. We support our claims with extensive and challenging cross-domain experiments for visual control.
Model-based Reinforcement Learning (MBRL) holds promise for data-efficiency by planning with model-generated experience in addition to learning with experience from the environment. However, in complex or changing environments, models in MBRL will inevitably be imperfect, and their detrimental effects on learning can be difficult to mitigate. In this work, we question whether the objective of these models should be the accurate simulation of environment dynamics at all. We focus our investigations on Dyna-style planning in a prediction setting. First, we highlight and support three motivating points: a perfectly accurate model of environment dynamics is not practically achievable, is not necessary, and is not always the most useful anyways. Second, we introduce a meta-learning algorithm for training models with a focus on their usefulness to the learner instead of their accuracy in modelling the environment. Our experiments show that in a simple non-stationary environment, our algorithm enables faster learning than even using an accurate model built with domain-specific knowledge of the non-stationarity.
Humans and animals can learn new skills after practicing for a few hours, while current reinforcement learning algorithms require a large amount of data to achieve good performances. Recent model-based approaches show promising results by reducing the number of necessary interactions with the environment to learn a desirable policy. However, these methods require biological implausible ingredients, such as the detailed storage of older experiences, and long periods of offline learning. The optimal way to learn and exploit word-models is still an open question. Taking inspiration from biology, we suggest that dreaming might be an efficient expedient to use an inner model. We propose a two-module (agent and model) spiking neural network in which "dreaming" (living new experiences in a model-based simulated environment) significantly boosts learning. We also explore "planning", an online alternative to dreaming, that shows comparable performances. Importantly, our model does not require the detailed storage of experiences, and learns online the world-model and the policy. Moreover, we stress that our network is composed of spiking neurons, further increasing the biological plausibility and implementability in neuromorphic hardware.
Model-based reinforcement learning methods often use learning only for the purpose of estimating an approximate dynamics model, offloading the rest of the decision-making work to classical trajectory optimizers. While conceptually simple, this combination has a number of empirical shortcomings, suggesting that learned models may not be well-suited to standard trajectory optimization. In this paper, we consider what it would look like to fold as much of the trajectory optimization pipeline as possible into the modeling problem, such that sampling from the model and planning with it become nearly identical. The core of our technical approach lies in a diffusion probabilistic model that plans by iteratively denoising trajectories. We show how classifier-guided sampling and image inpainting can be reinterpreted as coherent planning strategies, explore the unusual and useful properties of diffusion-based planning methods, and demonstrate the effectiveness of our framework in control settings that emphasize long-horizon decision-making and test-time flexibility.
This paper addresses the problem of learning control policies for mobile robots, modeled as unknown Markov Decision Processes (MDPs), that are tasked with temporal logic missions, such as sequencing, coverage, or surveillance. The MDP captures uncertainty in the workspace structure and the outcomes of control decisions. The control objective is to synthesize a control policy that maximizes the probability of accomplishing a high-level task, specified as a Linear Temporal Logic (LTL) formula. To address this problem, we propose a novel accelerated model-based reinforcement learning (RL) algorithm for LTL control objectives that is capable of learning control policies significantly faster than related approaches. Its sample-efficiency relies on biasing exploration towards directions that may contribute to task satisfaction. This is accomplished by leveraging an automaton representation of the LTL task as well as a continuously learned MDP model. Finally, we provide comparative experiments that demonstrate the sample efficiency of the proposed method against recent RL methods for LTL objectives.
Training deep learning models takes an extremely long execution time and consumes large amounts of computing resources. At the same time, recent research proposed systems and compilers that are expected to decrease deep learning models runtime. An effective optimisation methodology in data processing is desirable, and the reduction of compute requirements of deep learning models is the focus of extensive research. In this paper, we address the neural network sub-graph transformation by exploring reinforcement learning (RL) agents to achieve performance improvement. Our proposed approach RLFlow can learn to perform neural network subgraph transformations, without the need for expertly designed heuristics to achieve a high level of performance. Recent work has aimed at applying RL to computer systems with some success, especially using model-free RL techniques. Model-based reinforcement learning methods have seen an increased focus in research as they can be used to learn the transition dynamics of the environment; this can be leveraged to train an agent using a hallucinogenic environment such as World Model (WM), thereby increasing sample efficiency compared to model-free approaches. WM uses variational auto-encoders and it builds a model of the system and allows exploring the model in an inexpensive way. In RLFlow, we propose a design for a model-based agent with WM which learns to optimise the architecture of neural networks by performing a sequence of sub-graph transformations to reduce model runtime. We show that our approach can match the state-of-the-art performance on common convolutional networks and outperforms by up to 5% those based on transformer-style architectures
In recent years, a growing number of deep model-based reinforcement learning (RL) methods have been introduced. The interest in deep model-based RL is not surprising, given its many potential benefits, such as higher sample efficiency and the potential for fast adaption to changes in the environment. However, we demonstrate, using an improved version of the recently introduced Local Change Adaptation (LoCA) setup, that well-known model-based methods such as PlaNet and DreamerV2 perform poorly in their ability to adapt to local environmental changes. Combined with prior work that made a similar observation about the other popular model-based method, MuZero, a trend appears to emerge, suggesting that current deep model-based methods have serious limitations. We dive deeper into the causes of this poor performance, by identifying elements that hurt adaptive behavior and linking these to underlying techniques frequently used in deep model-based RL. We empirically validate these insights in the case of linear function approximation by demonstrating that a modified version of linear Dyna achieves effective adaptation to local changes. Furthermore, we provide detailed insights into the challenges of building an adaptive nonlinear model-based method, by experimenting with a nonlinear version of Dyna.
Sequential modelling of high-dimensional data is an important problem that appears in many domains including model-based reinforcement learning and dynamics identification for control. Latent variable models applied to sequential data (i.e., latent dynamics models) have been shown to be a particularly effective probabilistic approach to solve this problem, especially when dealing with images. However, in many application areas (e.g., robotics), information from multiple sensing modalities is available -- existing latent dynamics methods have not yet been extended to effectively make use of such multimodal sequential data. Multimodal sensor streams can be correlated in a useful manner and often contain complementary information across modalities. In this work, we present a self-supervised generative modelling framework to jointly learn a probabilistic latent state representation of multimodal data and the respective dynamics. Using synthetic and real-world datasets from a multimodal robotic planar pushing task, we demonstrate that our approach leads to significant improvements in prediction and representation quality. Furthermore, we compare to the common learning baseline of concatenating each modality in the latent space and show that our principled probabilistic formulation performs better. Finally, despite being fully self-supervised, we demonstrate that our method is nearly as effective as an existing supervised approach that relies on ground truth labels.
Model-based reinforcement learning (RL) algorithms designed for handling complex visual observations typically learn some sort of latent state representation, either explicitly or implicitly. Standard methods of this sort do not distinguish between functionally relevant aspects of the state and irrelevant distractors, instead aiming to represent all available information equally. We propose a modified objective for model-based RL that, in combination with mutual information maximization, allows us to learn representations and dynamics for visual model-based RL without reconstruction in a way that explicitly prioritizes functionally relevant factors. The key principle behind our design is to integrate a term inspired by variational empowerment into a state-space model based on mutual information. This term prioritizes information that is correlated with action, thus ensuring that functionally relevant factors are captured first. Furthermore, the same empowerment term also promotes faster exploration during the RL process, especially for sparse-reward tasks where the reward signal is insufficient to drive exploration in the early stages of learning. We evaluate the approach on a suite of vision-based robot control tasks with natural video backgrounds, and show that the proposed prioritized information objective outperforms state-of-the-art model based RL approaches with higher sample efficiency and episodic returns. https://sites.google.com/view/information-empowerment
The interaction between a vehicle navigation system and the driver of the vehicle can be formulated as a model-based reinforcement learning problem, where the navigation systems (agent) must quickly adapt to the characteristics of the driver (environmental dynamics) to provide the best sequence of turn-by-turn driving instructions. Most modern day navigation systems (e.g, Google maps, Waze, Garmin) are not designed to personalize their low-level interactions for individual users across a wide range of driving styles (e.g., vehicle type, reaction time, level of expertise). Towards the development of personalized navigation systems that adapt to a variety of driving styles, we propose an online no-regret model-based RL method that quickly conforms to the dynamics of the current user. As the user interacts with it, the navigation system quickly builds a user-specific model, from which navigation commands are optimized using model predictive control. By personalizing the policy in this way, our method is able to give well-timed driving instructions that match the user's dynamics. Our theoretical analysis shows that our method is a no-regret algorithm and we provide the convergence rate in the agnostic setting. Our empirical analysis with 60+ hours of real-world user data using a driving simulator shows that our method can reduce the number of collisions by more than 60%.
The objective of this research is to enable safety-critical systems to simultaneously learn and execute optimal control policies in a safe manner to achieve complex autonomy. Learning optimal policies via trial and error, i.e., traditional reinforcement learning, is difficult to implement in safety-critical systems, particularly when task restarts are unavailable. Safe model-based reinforcement learning techniques based on a barrier transformation have recently been developed to address this problem. However, these methods rely on full state feedback, limiting their usability in a real-world environment. In this work, an output-feedback safe model-based reinforcement learning technique based on a novel barrier-aware dynamic state estimator has been designed to address this issue. The developed approach facilitates simultaneous learning and execution of safe control policies for safety-critical linear systems. Simulation results indicate that barrier transformation is an effective approach to achieve online reinforcement learning in safety-critical systems using output feedback.
Model-based reinforcement learning (MBRL) is a sample efficient technique to obtain control policies, yet unavoidable modeling errors often lead performance deterioration. The model in MBRL is often solely fitted to reconstruct dynamics, state observations in particular, while the impact of model error on the policy is not captured by the training objective. This leads to a mismatch between the intended goal of MBRL, enabling good policy and value learning, and the target of the loss function employed in practice, future state prediction. Naive intuition would suggest that value-aware model learning would fix this problem and, indeed, several solutions to this objective mismatch problem have been proposed based on theoretical analysis. However, they tend to be inferior in practice to commonly used maximum likelihood (MLE) based approaches. In this paper we propose the Value-gradient weighted Model Learning (VaGraM), a novel method for value-aware model learning which improves the performance of MBRL in challenging settings, such as small model capacity and the presence of distracting state dimensions. We analyze both MLE and value-aware approaches and demonstrate how they fail to account for exploration and the behavior of function approximation when learning value-aware models and highlight the additional goals that must be met to stabilize optimization in the deep learning setting. We verify our analysis by showing that our loss function is able to achieve high returns on the Mujoco benchmark suite while being more robust than maximum likelihood based approaches.
Model-based value expansion methods promise to improve the quality of value function targets and, thereby, the effectiveness of value function learning. However, to date, these methods are being outperformed by Dyna-style algorithms with conceptually simpler 1-step value function targets. This shows that in practice, the theoretical justification of value expansion does not seem to hold. We provide a thorough empirical study to shed light on the causes of failure of value expansion methods in practice which is believed to be the compounding model error. By leveraging GPU based physics simulators, we are able to efficiently use the true dynamics for analysis inside the model-based reinforcement learning loop. Performing extensive comparisons between true and learned dynamics sheds light into this black box. This paper provides a better understanding of the actual problems in value expansion. We provide future directions of research by empirically testing the maximum theoretical performance of current approaches.
Accurately predicting the consequences of agents' actions is a key prerequisite for planning in robotic control. Model-based reinforcement learning (MBRL) is one paradigm which relies on the iterative learning and prediction of state-action transitions to solve a task. Deep MBRL has become a popular candidate, using a neural network to learn a dynamics model that predicts with each pass from high-dimensional states to actions. These "one-step" predictions are known to become inaccurate over longer horizons of composed prediction - called the compounding error problem. Given the prevalence of the compounding error problem in MBRL and related fields of data-driven control, we set out to understand the properties of and conditions causing these long-horizon errors. In this paper, we explore the effects of subcomponents of a control problem on long term prediction error: including choosing a system, collecting data, and training a model. These detailed quantitative studies on simulated and real-world data show that the underlying dynamics of a system are the strongest factor determining the shape and magnitude of prediction error. Given a clearer understanding of compounding prediction error, researchers can implement new types of models beyond "one-step" that are more useful for control.
Model-based reinforcement learning algorithms are typically more sample efficient than their model-free counterparts, especially in sparse reward problems. Unfortunately, many interesting domains are too complex to specify the complete models required by traditional model-based approaches. Learning a model takes a large number of environment samples, and may not capture critical information if the environment is hard to explore. If we could specify an incomplete model and allow the agent to learn how best to use it, we could take advantage of our partial understanding of many domains. Existing hybrid planning and learning systems which address this problem often impose highly restrictive assumptions on the sorts of models which can be used, limiting their applicability to a wide range of domains. In this work we propose SAGE, an algorithm combining learning and planning to exploit a previously unusable class of incomplete models. This combines the strengths of symbolic planning and neural learning approaches in a novel way that outperforms competing methods on variations of taxi world and Minecraft.
The present paper proposes a novel reinforcement learning method with world models, DreamingV2, a collaborative extension of DreamerV2 and Dreaming. DreamerV2 is a cutting-edge model-based reinforcement learning from pixels that uses discrete world models to represent latent states with categorical variables. Dreaming is also a form of reinforcement learning from pixels that attempts to avoid the autoencoding process in general world model training by involving a reconstruction-free contrastive learning objective. The proposed DreamingV2 is a novel approach of adopting both the discrete representation of DreamingV2 and the reconstruction-free objective of Dreaming. Compared to DreamerV2 and other recent model-based methods without reconstruction, DreamingV2 achieves the best scores on five simulated challenging 3D robot arm tasks. We believe that DreamingV2 will be a reliable solution for robot learning since its discrete representation is suitable to describe discontinuous environments, and the reconstruction-free fashion well manages complex vision observations.
The Dreamer agent provides various benefits of Model-Based Reinforcement Learning (MBRL) such as sample efficiency, reusable knowledge, and safe planning. However, its world model and policy networks inherit the limitations of recurrent neural networks and thus an important question is how an MBRL framework can benefit from the recent advances of transformers and what the challenges are in doing so. In this paper, we propose a transformer-based MBRL agent, called TransDreamer. We first introduce the Transformer State-Space Model, a world model that leverages a transformer for dynamics predictions. We then share this world model with a transformer-based policy network and obtain stability in training a transformer-based RL agent. In experiments, we apply the proposed model to 2D visual RL and 3D first-person visual RL tasks both requiring long-range memory access for memory-based reasoning. We show that the proposed model outperforms Dreamer in these complex tasks.
Most recommender systems are myopic, that is they optimize based on the immediate response of the user. This may be misaligned with the true objective, such as creating long term user satisfaction. In this work we focus on mobile push notifications, where the long term effects of recommender system decisions can be particularly strong. For example, sending too many or irrelevant notifications may annoy a user and cause them to disable notifications. However, a myopic system will always choose to send a notification since negative effects occur in the future. This is typically mitigated using heuristics. However, heuristics can be hard to reason about or improve, require retuning each time the system is changed, and may be suboptimal. To counter these drawbacks, there is significant interest in recommender systems that optimize directly for long-term value (LTV). Here, we describe a method for maximising LTV by using model-based reinforcement learning (RL) to make decisions about whether to send push notifications. We model the effects of sending a notification on the user's future behavior. Much of the prior work applying RL to maximise LTV in recommender systems has focused on session-based optimization, while the time horizon for notification decision making in this work extends over several days. We test this approach in an A/B test on a major social network. We show that by optimizing decisions about push notifications we are able to send less notifications and obtain a higher open rate than the baseline system, while generating the same level of user engagement on the platform as the existing, heuristic-based, system.