Deep reinforcement learning (DRL) has shown significant promise for uncovering sophisticated control policies that interact in environments with complicated dynamics, such as stabilizing the magnetohydrodynamics of a tokamak fusion reactor or minimizing the drag force exerted on an object in a fluid flow. However, these algorithms require an abundance of training examples and may become prohibitively expensive for many applications. In addition, the reliance on deep neural networks often results in an uninterpretable, black-box policy that may be too computationally expensive to use with certain embedded systems. Recent advances in sparse dictionary learning, such as the sparse identification of nonlinear dynamics (SINDy), have shown promise for creating efficient and interpretable data-driven models in the low-data regime. In this work we introduce SINDy-RL, a unifying framework for combining SINDy and DRL to create efficient, interpretable, and trustworthy representations of the dynamics model, reward function, and control policy. We demonstrate the effectiveness of our approaches on benchmark control environments and challenging fluids problems. SINDy-RL achieves comparable performance to state-of-the-art DRL algorithms using significantly fewer interactions in the environment and results in an interpretable control policy orders of magnitude smaller than a deep neural network policy.
Current model-based reinforcement learning (MBRL) agents struggle with long-term dependencies. This limits their ability to effectively solve tasks involving extended time gaps between actions and outcomes, or tasks demanding the recalling of distant observations to inform current actions. To improve temporal coherence, we integrate a new family of state space models (SSMs) in world models of MBRL agents to present a new method, Recall to Imagine (R2I). This integration aims to enhance both long-term memory and long-horizon credit assignment. Through a diverse set of illustrative tasks, we systematically demonstrate that R2I not only establishes a new state-of-the-art for challenging memory and credit assignment RL tasks, such as BSuite and POPGym, but also showcases superhuman performance in the complex memory domain of Memory Maze. At the same time, it upholds comparable performance in classic RL tasks, such as Atari and DMC, suggesting the generality of our method. We also show that R2I is faster than the state-of-the-art MBRL method, DreamerV3, resulting in faster wall-time convergence.
Recent research has shown the potential of Model-based Reinforcement Learning (MBRL) to enhance energy efficiency of Heating, Ventilation, and Air Conditioning (HVAC) systems. However, existing methods rely on black-box thermal dynamics models and stochastic optimizers, lacking reliability guarantees and posing risks to occupant health. In this work, we overcome the reliability bottleneck by redesigning HVAC controllers using decision trees extracted from existing thermal dynamics models and historical data. Our decision tree-based policies are deterministic, verifiable, interpretable, and more energy-efficient than current MBRL methods. First, we introduce a novel verification criterion for RL agents in HVAC control based on domain knowledge. Second, we develop a policy extraction procedure that produces a verifiable decision tree policy. We found that the high dimensionality of the thermal dynamics model input hinders the efficiency of policy extraction. To tackle the dimensionality challenge, we leverage importance sampling conditioned on historical data distributions, significantly improving policy extraction efficiency. Lastly, we present an offline verification algorithm that guarantees the reliability of a control policy. Extensive experiments show that our method saves 68.4% more energy and increases human comfort gain by 14.8% compared to the state-of-the-art method, in addition to an 1127x reduction in computation overhead. Our code and data are available at https://github.com/ryeii/Veri_HVAC
Model-based reinforcement learning (MBRL) has been a primary approach to ameliorating the sample efficiency issue as well as to make a generalist agent. However, there has not been much effort toward enhancing the strategy of dreaming itself. Therefore, it is a question whether and how an agent can "dream better" in a more structured and strategic way. In this paper, inspired by the observation from cognitive science suggesting that humans use a spatial divide-and-conquer strategy in planning, we propose a new MBRL agent, called Dr. Strategy, which is equipped with a novel Dreaming Strategy. The proposed agent realizes a version of divide-and-conquer-like strategy in dreaming. This is achieved by learning a set of latent landmarks and then utilizing these to learn a landmark-conditioned highway policy. With the highway policy, the agent can first learn in the dream to move to a landmark, and from there it tackles the exploration and achievement task in a more focused way. In experiments, we show that the proposed model outperforms prior pixel-based MBRL methods in various visually complex and partially observable navigation tasks.
In recent years, deep reinforcement learning has emerged as a technique to solve closed-loop flow control problems. Employing simulation-based environments in reinforcement learning enables a priori end-to-end optimization of the control system, provides a virtual testbed for safety-critical control applications, and allows to gain a deep understanding of the control mechanisms. While reinforcement learning has been applied successfully in a number of rather simple flow control benchmarks, a major bottleneck toward real-world applications is the high computational cost and turnaround time of flow simulations. In this contribution, we demonstrate the benefits of model-based reinforcement learning for flow control applications. Specifically, we optimize the policy by alternating between trajectories sampled from flow simulations and trajectories sampled from an ensemble of environment models. The model-based learning reduces the overall training time by up to $85\%$ for the fluidic pinball test case. Even larger savings are expected for more demanding flow simulations.
In an unfamiliar setting, a model-based reinforcement learning agent can be limited by the accuracy of its world model. In this work, we present a novel, training-free approach to improving the performance of such agents separately from planning and learning. We do so by applying iterative inference at decision-time, to fine-tune the inferred agent states based on the coherence of future state representations. Our approach achieves a consistent improvement in both reconstruction accuracy and task performance when applied to visual 3D navigation tasks. We go on to show that considering more future states further improves the performance of the agent in partially-observable environments, but not in a fully-observable one. Finally, we demonstrate that agents with less training pre-evaluation benefit most from our approach.
Mathematical and computational tools have proven to be reliable in decision-making processes. In recent times, in particular, machine learning-based methods are becoming increasingly popular as advanced support tools. When dealing with control problems, reinforcement learning has been applied to decision-making in several applications, most notably in games. The success of these methods in finding solutions to complex problems motivates the exploration of new areas where they can be employed to overcome current difficulties. In this paper, we explore the use of automatic control strategies to initial boundary value problems in thermal and disease transport. Specifically, in this work, we adapt an existing reinforcement learning algorithm using a stochastic policy gradient method and we introduce two novel reward functions to drive the flow of the transported field. The new model-based framework exploits the interactions between a reaction-diffusion model and the modified agent. The results show that certain controls can be implemented successfully in these applications, although model simplifications had to be assumed.
Offline reinforcement learning aims to train agents from pre-collected datasets. However, this comes with the added challenge of estimating the value of behaviors not covered in the dataset. Model-based methods offer a potential solution by training an approximate dynamics model, which then allows collection of additional synthetic data via rollouts in this model. The prevailing theory treats this approach as online RL in an approximate dynamics model, and any remaining performance gap is therefore understood as being due to dynamics model errors. In this paper, we analyze this assumption and investigate how popular algorithms perform as the learned dynamics model is improved. In contrast to both intuition and theory, if the learned dynamics model is replaced by the true error-free dynamics, existing model-based methods completely fail. This reveals a key oversight: The theoretical foundations assume sampling of full horizon rollouts in the learned dynamics model; however, in practice, the number of model-rollout steps is aggressively reduced to prevent accumulating errors. We show that this truncation of rollouts results in a set of edge-of-reach states at which we are effectively ``bootstrapping from the void.'' This triggers pathological value overestimation and complete performance collapse. We term this the edge-of-reach problem. Based on this new insight, we fill important gaps in existing theory, and reveal how prior model-based methods are primarily addressing the edge-of-reach problem, rather than model-inaccuracy as claimed. Finally, we propose Reach-Aware Value Learning (RAVL), a simple and robust method that directly addresses the edge-of-reach problem and hence - unlike existing methods - does not fail as the dynamics model is improved. Code open-sourced at: github.com/anyasims/edge-of-reach.
This study tackles the challenges of adversarial corruption in model-based reinforcement learning (RL), where the transition dynamics can be corrupted by an adversary. Existing studies on corruption-robust RL mostly focus on the setting of model-free RL, where robust least-square regression is often employed for value function estimation. However, these techniques cannot be directly applied to model-based RL. In this paper, we focus on model-based RL and take the maximum likelihood estimation (MLE) approach to learn transition model. Our work encompasses both online and offline settings. In the online setting, we introduce an algorithm called corruption-robust optimistic MLE (CR-OMLE), which leverages total-variation (TV)-based information ratios as uncertainty weights for MLE. We prove that CR-OMLE achieves a regret of $\tilde{\mathcal{O}}(\sqrt{T} + C)$, where $C$ denotes the cumulative corruption level after $T$ episodes. We also prove a lower bound to show that the additive dependence on $C$ is optimal. We extend our weighting technique to the offline setting, and propose an algorithm named corruption-robust pessimistic MLE (CR-PMLE). Under a uniform coverage condition, CR-PMLE exhibits suboptimality worsened by $\mathcal{O}(C/n)$, nearly matching the lower bound. To the best of our knowledge, this is the first work on corruption-robust model-based RL algorithms with provable guarantees.
This paper contributes a new approach for distributional reinforcement learning which elucidates a clean separation of transition structure and reward in the learning process. Analogous to how the successor representation (SR) describes the expected consequences of behaving according to a given policy, our distributional successor measure (SM) describes the distributional consequences of this behaviour. We formulate the distributional SM as a distribution over distributions and provide theory connecting it with distributional and model-based reinforcement learning. Moreover, we propose an algorithm that learns the distributional SM from data by minimizing a two-level maximum mean discrepancy. Key to our method are a number of algorithmic techniques that are independently valuable for learning generative models of state. As an illustration of the usefulness of the distributional SM, we show that it enables zero-shot risk-sensitive policy evaluation in a way that was not previously possible.
Leveraging planning during learning and decision-making is central to the long-term development of intelligent agents. Recent works have successfully combined tree-based search methods and self-play learning mechanisms to this end. However, these methods typically face scaling challenges due to the sequential nature of their search. While practical engineering solutions can partly overcome this, they often result in a negative impact on performance. In this paper, we introduce SPO: Sequential Monte Carlo Policy Optimisation, a model-based reinforcement learning algorithm grounded within the Expectation Maximisation (EM) framework. We show that SPO provides robust policy improvement and efficient scaling properties. The sample-based search makes it directly applicable to both discrete and continuous action spaces without modifications. We demonstrate statistically significant improvements in performance relative to model-free and model-based baselines across both continuous and discrete environments. Furthermore, the parallel nature of SPO's search enables effective utilisation of hardware accelerators, yielding favourable scaling laws.
We address private deep offline reinforcement learning (RL), where the goal is to train a policy on standard control tasks that is differentially private (DP) with respect to individual trajectories in the dataset. To achieve this, we introduce PriMORL, a model-based RL algorithm with formal differential privacy guarantees. PriMORL first learns an ensemble of trajectory-level DP models of the environment from offline data. It then optimizes a policy on the penalized private model, without any further interaction with the system or access to the dataset. In addition to offering strong theoretical foundations, we demonstrate empirically that PriMORL enables the training of private RL agents on offline continuous control tasks with deep function approximations, whereas current methods are limited to simpler tabular and linear Markov Decision Processes (MDPs). We furthermore outline the trade-offs involved in achieving privacy in this setting.
We consider the problem of offline reinforcement learning where only a set of system transitions is made available for policy optimization. Following recent advances in the field, we consider a model-based reinforcement learning algorithm that infers the system dynamics from the available data and performs policy optimization on imaginary model rollouts. This approach is vulnerable to exploiting model errors which can lead to catastrophic failures on the real system. The standard solution is to rely on ensembles for uncertainty heuristics and to avoid exploiting the model where it is too uncertain. We challenge the popular belief that we must resort to ensembles by showing that better performance can be obtained with a single well-calibrated autoregressive model on the D4RL benchmark. We also analyze static metrics of model-learning and conclude on the important model properties for the final performance of the agent.
In model-based reinforcement learning, most algorithms rely on simulating trajectories from one-step models of the dynamics learned on data. A critical challenge of this approach is the compounding of one-step prediction errors as the length of the trajectory grows. In this paper we tackle this issue by using a multi-step objective to train one-step models. Our objective is a weighted sum of the mean squared error (MSE) loss at various future horizons. We find that this new loss is particularly useful when the data is noisy (additive Gaussian noise in the observations), which is often the case in real-life environments. To support the multi-step loss, first we study its properties in two tractable cases: i) uni-dimensional linear system, and ii) two-parameter non-linear system. Second, we show in a variety of tasks (environments or datasets) that the models learned with this loss achieve a significant improvement in terms of the averaged R2-score on future prediction horizons. Finally, in the pure batch reinforcement learning setting, we demonstrate that one-step models serve as strong baselines when dynamics are deterministic, while multi-step models would be more advantageous in the presence of noise, highlighting the potential of our approach in real-world applications.
In this paper we are introducing a new reinforcement learning method for control problems in environments with delayed feedback. Specifically, our method employs stochastic planning, versus previous methods that used deterministic planning. This allows us to embed risk preference in the policy optimization problem. We show that this formulation can recover the optimal policy for problems with deterministic transitions. We contrast our policy with two prior methods from literature. We apply the methodology to simple tasks to understand its features. Then, we compare the performance of the methods in controlling multiple Atari games.
Training task-oriented dialog agents based on reinforcement learning is time-consuming and requires a large number of interactions with real users. How to grasp dialog policy within limited dialog experiences remains an obstacle that makes the agent training process less efficient. In addition, most previous frameworks start training by randomly choosing training samples, which differs from the human learning method and hurts the efficiency and stability of training. Therefore, we propose Scheduled Curiosity-Deep Dyna-Q (SC-DDQ), a curiosity-driven curriculum learning framework based on a state-of-the-art model-based reinforcement learning dialog model, Deep Dyna-Q (DDQ). Furthermore, we designed learning schedules for SC-DDQ and DDQ, respectively, following two opposite training strategies: classic curriculum learning and its reverse version. Our results show that by introducing scheduled learning and curiosity, the new framework leads to a significant improvement over the DDQ and Deep Q-learning(DQN). Surprisingly, we found that traditional curriculum learning was not always effective. Specifically, according to the experimental results, the easy-first and difficult-first strategies are more suitable for SC-DDQ and DDQ. To analyze our results, we adopted the entropy of sampled actions to depict action exploration and found that training strategies with high entropy in the first stage and low entropy in the last stage lead to better performance.
Continual RL requires an agent to learn new tasks without forgetting previous ones, while improving on both past and future tasks. The most common approaches use model-free algorithms and replay buffers can help to mitigate catastrophic forgetting, but often struggle with scalability due to large memory requirements. Biologically inspired replay suggests replay to a world model, aligning with model-based RL; as opposed to the common setting of replay in model-free algorithms. Model-based RL offers benefits for continual RL by leveraging knowledge of the environment, independent of policy. We introduce WMAR (World Models with Augmented Replay), a model-based RL algorithm with a memory-efficient distribution-matching replay buffer. WMAR extends the well known DreamerV3 algorithm, which employs a simple FIFO buffer and was not tested in continual RL. We evaluated WMAR and DreamerV3, with the same-size replay buffers. They were tested on two scenarios: tasks with shared structure using OpenAI Procgen and tasks without shared structure using the Atari benchmark. WMAR demonstrated favourable properties for continual RL considering metrics for forgetting as well as skill transfer on past and future tasks. Compared to DreamerV3, WMAR showed slight benefits in tasks with shared structure and substantially better forgetting characteristics on tasks without shared structure. Our results suggest that model-based RL with a memory-efficient replay buffer can be an effective approach to continual RL, justifying further research.
Acquiring an accurate world model online for model-based reinforcement learning (MBRL) is challenging due to data nonstationarity, which typically causes catastrophic forgetting for neural networks (NNs). From the online learning perspective, a Follow-The-Leader (FTL) world model is desirable, which optimally fits all previous experiences at each round. Unfortunately, NN-based models need re-training on all accumulated data at every interaction step to achieve FTL, which is computationally expensive for lifelong agents. In this paper, we revisit models that can achieve FTL with incremental updates. Specifically, our world model is a linear regression model supported by nonlinear random features. The linear part ensures efficient FTL update while the nonlinear random feature empowers the fitting of complex environments. To best trade off model capacity and computation efficiency, we introduce a locality sensitive sparse encoding, which allows us to conduct efficient sparse updates even with very high dimensional nonlinear features. We validate the representation power of our encoding and verify that it allows efficient online learning under data covariate shift. We also show, in the Dyna MBRL setting, that our world models learned online using a single pass of trajectory data either surpass or match the performance of deep world models trained with replay and other continual learning methods.
Sampling-based Model Predictive Control (MPC) has been a practical and effective approach in many domains, notably model-based reinforcement learning, thanks to its flexibility and parallelizability. Despite its appealing empirical performance, the theoretical understanding, particularly in terms of convergence analysis and hyperparameter tuning, remains absent. In this paper, we characterize the convergence property of a widely used sampling-based MPC method, Model Predictive Path Integral Control (MPPI). We show that MPPI enjoys at least linear convergence rates when the optimization is quadratic, which covers time-varying LQR systems. We then extend to more general nonlinear systems. Our theoretical analysis directly leads to a novel sampling-based MPC algorithm, CoVariance-Optimal MPC (CoVo-MPC) that optimally schedules the sampling covariance to optimize the convergence rate. Empirically, CoVo-MPC significantly outperforms standard MPPI by 43-54% in both simulations and real-world quadrotor agile control tasks. Videos and Appendices are available at \url{https://lecar-lab.github.io/CoVO-MPC/}.
Direct imaging of Earth-like exoplanets is one of the most prominent scientific drivers of the next generation of ground-based telescopes. Typically, Earth-like exoplanets are located at small angular separations from their host stars, making their detection difficult. Consequently, the adaptive optics (AO) system's control algorithm must be carefully designed to distinguish the exoplanet from the residual light produced by the host star. A new promising avenue of research to improve AO control builds on data-driven control methods such as Reinforcement Learning (RL). RL is an active branch of the machine learning research field, where control of a system is learned through interaction with the environment. Thus, RL can be seen as an automated approach to AO control, where its usage is entirely a turnkey operation. In particular, model-based reinforcement learning (MBRL) has been shown to cope with both temporal and misregistration errors. Similarly, it has been demonstrated to adapt to non-linear wavefront sensing while being efficient in training and execution. In this work, we implement and adapt an RL method called Policy Optimization for AO (PO4AO) to the GHOST test bench at ESO headquarters, where we demonstrate a strong performance of the method in a laboratory environment. Our implementation allows the training to be performed parallel to inference, which is crucial for on-sky operation. In particular, we study the predictive and self-calibrating aspects of the method. The new implementation on GHOST running PyTorch introduces only around 700 microseconds in addition to hardware, pipeline, and Python interface latency. We open-source well-documented code for the implementation and specify the requirements for the RTC pipeline. We also discuss the important hyperparameters of the method, the source of the latency, and the possible paths for a lower latency implementation.