Model-based reinforcement learning (MBRL) algorithms learn a dynamics model from collected data and apply it to generate synthetic trajectories to enable faster learning. This is an especially promising paradigm in offline reinforcement learning (RL) where data may be limited in quantity, in addition to being deficient in coverage and quality. Practical approaches to offline MBRL usually rely on ensembles of dynamics models to prevent exploitation of any individual model and to extract uncertainty estimates that penalize values in states far from the dataset support. Uncertainty estimates from ensembles can vary greatly in scale, making it challenging to generalize hyperparameters well across even similar tasks. In this paper, we present Morse Model-based offline RL (MoMo), which extends the anti-exploration paradigm found in offline model-free RL to the model-based space. We develop model-free and model-based variants of MoMo and show how the model-free version can be extended to detect and deal with out-of-distribution (OOD) states using explicit uncertainty estimation without the need for large ensembles. MoMo performs offline MBRL using an anti-exploration bonus to counteract value overestimation in combination with a policy constraint, as well as a truncation function to terminate synthetic rollouts that are excessively OOD. Experimentally, we find that both model-free and model-based MoMo perform well, and the latter outperforms prior model-based and model-free baselines on the majority of D4RL datasets tested.
Learning a transition model via Maximum Likelihood Estimation (MLE) followed by planning inside the learned model is perhaps the most standard and simplest Model-based Reinforcement Learning (RL) framework. In this work, we show that such a simple Model-based RL scheme, when equipped with optimistic and pessimistic planning procedures, achieves strong regret and sample complexity bounds in online and offline RL settings. Particularly, we demonstrate that under the conditions where the trajectory-wise reward is normalized between zero and one and the transition is time-homogenous, it achieves nearly horizon-free and second-order bounds. Nearly horizon-free means that our bounds have no polynomial dependence on the horizon of the Markov Decision Process. A second-order bound is a type of instance-dependent bound that scales with respect to the variances of the returns of the policies which can be small when the system is nearly deterministic and (or) the optimal policy has small values. We highlight that our algorithms are simple, fairly standard, and indeed have been extensively studied in the RL literature: they learn a model via MLE, build a version space around the MLE solution, and perform optimistic or pessimistic planning depending on whether operating in the online or offline mode. These algorithms do not rely on additional specialized algorithmic designs such as learning variances and performing variance-weighted learning and thus can easily leverage non-linear function approximations. The simplicity of the algorithms also implies that our horizon-free and second-order regret analysis is actually standard and mainly follows the general framework of optimism/pessimism in the face of uncertainty.
Interpretability of deep reinforcement learning systems could assist operators with understanding how they interact with their environment. Vector quantization methods -- also called codebook methods -- discretize a neural network's latent space that is often suggested to yield emergent interpretability. We investigate whether vector quantization in fact provides interpretability in model-based reinforcement learning. Our experiments, conducted in the reinforcement learning environment Crafter, show that the codes of vector quantization models are inconsistent, have no guarantee of uniqueness, and have a limited impact on concept disentanglement, all of which are necessary traits for interpretability. We share insights on why vector quantization may be fundamentally insufficient for model interpretability.
Animals flexibly change their behavior depending on context. It is reported that the hippocampus is one of the most prominent regions for contextual behaviors, and its sequential activity shows context dependency. However, how such context-dependent sequential activity is established through reorganization of neuronal activity (remapping) is unclear. To better understand the formation of hippocampal activity and its contribution to context-dependent flexible behavior, we present a novel biologically plausible reinforcement learning model. In this model, a context-selection module promotes the formation of context-dependent sequential activity and allows for flexible switching of behavior in multiple contexts. This model reproduces a variety of findings from neural activity, optogenetic inactivation, human fMRI, and clinical research. Furthermore, our model predicts that imbalances in the ratio between sensory and contextual inputs in the context-selection module account for schizophrenia (SZ) and autism spectrum disorder (ASD)-like behaviors.
Model-Based Reinforcement Learning (MBRL) has been widely studied for Heating, Ventilation, and Air Conditioning (HVAC) control in buildings. One of the critical challenges is the large amount of data required to effectively train neural networks for modeling building dynamics. This paper presents CLUE, an MBRL system for HVAC control in buildings. CLUE optimizes HVAC operations by integrating a Gaussian Process (GP) model to model building dynamics with uncertainty awareness. CLUE utilizes GP to predict state transitions as Gaussian distributions, effectively capturing prediction uncertainty and enhancing decision-making under sparse data conditions. Our approach employs a meta-kernel learning technique to efficiently set GP kernel hyperparameters using domain knowledge from diverse buildings. This drastically reduces the data requirements typically associated with GP models in HVAC applications. Additionally, CLUE incorporates these uncertainty estimates into a Model Predictive Path Integral (MPPI) algorithm, enabling the selection of safe, energy-efficient control actions. This uncertainty-aware control strategy evaluates and selects action trajectories based on their predicted impact on energy consumption and human comfort, optimizing operations even under uncertain conditions. Extensive simulations in a five-zone office building demonstrate that CLUE reduces the required training data from hundreds of days to just seven while maintaining robust control performance. It reduces comfort violations by an average of 12.07% compared to existing MBRL methods, without compromising on energy efficiency.
The application of learning-based control methods in robotics presents significant challenges. One is that model-free reinforcement learning algorithms use observation data with low sample efficiency. To address this challenge, a prevalent approach is model-based reinforcement learning, which involves employing an environment dynamics model. We suggest approximating transition dynamics with symbolic expressions, which are generated via symbolic regression. Approximation of a mechanical system with a symbolic model has fewer parameters than approximation with neural networks, which can potentially lead to higher accuracy and quality of extrapolation. We use a symbolic dynamics model to generate trajectories in model-based policy optimization to improve the sample efficiency of the learning algorithm. We evaluate our approach across various tasks within simulated environments. Our method demonstrates superior sample efficiency in these tasks compared to model-free and model-based baseline methods.
Offline model-based reinforcement learning (MBRL) enhances data efficiency by utilizing pre-collected datasets to learn models and policies, especially in scenarios where exploration is costly or infeasible. Nevertheless, its performance often suffers from the objective mismatch between model and policy learning, resulting in inferior performance despite accurate model predictions. This paper first identifies the primary source of this mismatch comes from the underlying confounders present in offline data for MBRL. Subsequently, we introduce \textbf{B}ilin\textbf{E}ar \textbf{CAUS}al r\textbf{E}presentation~(BECAUSE), an algorithm to capture causal representation for both states and actions to reduce the influence of the distribution shift, thus mitigating the objective mismatch problem. Comprehensive evaluations on 18 tasks that vary in data quality and environment context demonstrate the superior performance of BECAUSE over existing offline RL algorithms. We show the generalizability and robustness of BECAUSE under fewer samples or larger numbers of confounders. Additionally, we offer theoretical analysis of BECAUSE to prove its error bound and sample efficiency when integrating causal representation into offline MBRL.
Multi-agent systems (MAS) constitute a significant role in exploring machine intelligence and advanced applications. In order to deeply investigate complicated interactions within MAS scenarios, we originally propose "GNN for MBRL" model, which utilizes a state-spaced Graph Neural Networks with Model-based Reinforcement Learning to address specific MAS missions (e.g., Billiard-Avoidance, Autonomous Driving Cars). In detail, we firstly used GNN model to predict future states and trajectories of multiple agents, then applied the Cross-Entropy Method (CEM) optimized Model Predictive Control to assist the ego-agent planning actions and successfully accomplish certain MAS tasks.
Offline Safe Reinforcement Learning (RL) seeks to address safety constraints by learning from static datasets and restricting exploration. However, these approaches heavily rely on the dataset and struggle to generalize to unseen scenarios safely. In this paper, we aim to improve safety during the deployment of vision-based robotic tasks through online fine-tuning an offline pretrained policy. To facilitate effective fine-tuning, we introduce model-based RL, which is known for its data efficiency. Specifically, our method employs in-sample optimization to improve offline training efficiency while incorporating reachability guidance to ensure safety. After obtaining an offline safe policy, a safe policy expansion approach is leveraged for online fine-tuning. The performance of our method is validated on simulation benchmarks with five vision-only tasks and through real-world robot deployment using limited data. It demonstrates that our approach significantly improves the generalization of offline policies to unseen safety-constrained scenarios. To the best of our knowledge, this is the first work to explore offline-to-online RL for safe generalization tasks.
Secure data management and effective data sharing have become paramount in the rapidly evolving healthcare landscape, especially with the growing integration of the Internet of Medical Things (IoMT). The rise of generative artificial intelligence has further elevated Multi-modal Large Language Models (MLLMs) as essential tools for managing and optimizing healthcare data in IoMT. MLLMs can support multi-modal inputs and generate diverse types of content by leveraging large-scale training on vast amounts of multi-modal data. However, critical challenges persist in developing medical MLLMs, including security and freshness issues of healthcare data, affecting the output quality of MLLMs. To this end, in this paper, we propose a hybrid Retrieval-Augmented Generation (RAG)-empowered medical MLLM framework for healthcare data management. This framework leverages a hierarchical cross-chain architecture to facilitate secure data training. Moreover, it enhances the output quality of MLLMs through hybrid RAG, which employs multi-modal metrics to filter various unimodal RAG results and incorporates these retrieval results as additional inputs to MLLMs. Additionally, we employ age of information to indirectly evaluate the data freshness impact of MLLMs and utilize contract theory to incentivize healthcare data holders to share their fresh data, mitigating information asymmetry during data sharing. Finally, we utilize a generative diffusion model-based deep reinforcement learning algorithm to identify the optimal contract for efficient data sharing. Numerical results demonstrate the effectiveness of the proposed schemes, which achieve secure and efficient healthcare data management.
The identification of a mathematical dynamics model is a crucial step in the designing process of a controller. However, it is often very difficult to identify the system's governing equations, especially in complex environments that combine physical laws of different disciplines. In this paper, we present a new approach that allows identifying an ordinary differential equation by means of a physics-informed machine learning algorithm. Our method introduces a special neural network that allows exploiting prior human knowledge to a certain degree and extends it autonomously, so that the resulting differential equations describe the system as accurately as possible. We validate the method on a Duffing oscillator with simulation data and, additionally, on a cascaded tank example with real-world data. Subsequently, we use the developed algorithm in a model-based reinforcement learning framework by alternately identifying and controlling a system to a target state. We test the performance by swinging-up an inverted pendulum on a cart.
In this paper, a novel online, output-feedback, critic-only, model-based reinforcement learning framework is developed for safety-critical control systems operating in complex environments. The developed framework ensures system stability and safety, regardless of the lack of full-state measurement, while learning and implementing an optimal controller. The approach leverages linear matrix inequality-based observer design method to efficiently search for observer gains for effective state estimation. Then, approximate dynamic programming is used to develop an approximate controller that uses simulated experiences to guarantee the safety and stability of the closed-loop system. Safety is enforced by adding a recentered robust Lyapunov-like barrier function to the cost function that effectively enforces safety constraints, even in the presence of uncertainty in the state. Lyapunov-based stability analysis is used to guarantee uniform ultimate boundedness of the trajectories of the closed-loop system and ensure safety. Simulation studies are performed to demonstrate the effectiveness of the developed method through two real-world safety-critical scenarios, ensuring that the state trajectories of a given system remain in a given set and obstacle avoidance.
In model-based reinforcement learning, simulated experiences from the learned model are often treated as equivalent to experience from the real environment. However, when the model is inaccurate, it can catastrophically interfere with policy learning. Alternatively, the agent might learn about the model's accuracy and selectively use it only when it can provide reliable predictions. We empirically explore model uncertainty measures for selective planning and show that best results require distribution insensitive inference to estimate the uncertainty over model-based updates. To that end, we propose and evaluate bounding-box inference, which operates on bounding-boxes around sets of possible states and other quantities. We find that bounding-box inference can reliably support effective selective planning.
We study model-based reinforcement learning with non-linear function approximation where the transition function of the underlying Markov decision process (MDP) is given by a multinomial logistic (MNL) model. We develop a provably efficient discounted value iteration-based algorithm that works for both infinite-horizon average-reward and discounted-reward settings. For average-reward communicating MDPs, the algorithm guarantees a regret upper bound of $\tilde{\mathcal{O}}(dD\sqrt{T})$ where $d$ is the dimension of feature mapping, $D$ is the diameter of the underlying MDP, and $T$ is the horizon. For discounted-reward MDPs, our algorithm achieves $\tilde{\mathcal{O}}(d(1-\gamma)^{-2}\sqrt{T})$ regret where $\gamma$ is the discount factor. Then we complement these upper bounds by providing several regret lower bounds. We prove a lower bound of $\Omega(d\sqrt{DT})$ for learning communicating MDPs of diameter $D$ and a lower bound of $\Omega(d(1-\gamma)^{3/2}\sqrt{T})$ for learning discounted-reward MDPs with discount factor $\gamma$. Lastly, we show a regret lower bound of $\Omega(dH^{3/2}\sqrt{K})$ for learning $H$-horizon episodic MDPs with MNL function approximation where $K$ is the number of episodes, which improves upon the best-known lower bound for the finite-horizon setting.
Reinforcement learning has demonstrated impressive performance in various challenging problems such as robotics, board games, and classical arcade games. However, its real-world applications can be hindered by the absence of robustness and safety in the learned policies. More specifically, an RL agent that trains in a certain Markov decision process (MDP) often struggles to perform well in nearly identical MDPs. To address this issue, we employ the framework of Robust MDPs (RMDPs) in a model-based setting and introduce a novel learned transition model. Our method specifically incorporates an auxiliary pessimistic model, updated adversarially, to estimate the worst-case MDP within a Kullback-Leibler uncertainty set. In comparison to several existing works, our work does not impose any additional conditions on the training environment, such as the need for a parametric simulator. To test the effectiveness of the proposed pessimistic model in enhancing policy robustness, we integrate it into a practical RL algorithm, called Robust Model-Based Policy Optimization (RMBPO). Our experimental results indicate a notable improvement in policy robustness on high-dimensional MuJoCo control tasks, with the auxiliary model enhancing the performance of the learned policy in distorted MDPs. We further explore the learned deviation between the proposed auxiliary world model and the nominal model, to examine how pessimism is achieved. By learning a pessimistic world model and demonstrating its role in improving policy robustness, our research contributes towards making (model-based) RL more robust.
Adaptive brain stimulation can treat neurological conditions such as Parkinson's disease and post-stroke motor deficits by influencing abnormal neural activity. Because of patient heterogeneity, each patient requires a unique stimulation policy to achieve optimal neural responses. Model-free reinforcement learning (MFRL) holds promise in learning effective policies for a variety of similar control tasks, but is limited in domains like brain stimulation by a need for numerous costly environment interactions. In this work we introduce Coprocessor Actor Critic, a novel, model-based reinforcement learning (MBRL) approach for learning neural coprocessor policies for brain stimulation. Our key insight is that coprocessor policy learning is a combination of learning how to act optimally in the world and learning how to induce optimal actions in the world through stimulation of an injured brain. We show that our approach overcomes the limitations of traditional MFRL methods in terms of sample efficiency and task success and outperforms baseline MBRL approaches in a neurologically realistic model of an injured brain.
Optimizing the deployment of large language models (LLMs) in edge computing environments is critical for enhancing privacy and computational efficiency. Toward efficient wireless LLM inference in edge computing, this study comprehensively analyzes the impact of different splitting points in mainstream open-source LLMs. On this basis, this study introduces a framework taking inspiration from model-based reinforcement learning (MBRL) to determine the optimal splitting point across the edge and user equipment (UE). By incorporating a reward surrogate model, our approach significantly reduces the computational cost of frequent performance evaluations. Extensive simulations demonstrate that this method effectively balances inference performance and computational load under varying network conditions, providing a robust solution for LLM deployment in decentralized settings.
Quantum machine learning models use encoding circuits to map data into a quantum Hilbert space. While it is well known that the architecture of these circuits significantly influences core properties of the resulting model, they are often chosen heuristically. In this work, we present a novel approach using reinforcement learning techniques to generate problem-specific encoding circuits to improve the performance of quantum machine learning models. By specifically using a model-based reinforcement learning algorithm, we reduce the number of necessary circuit evaluations during the search, providing a sample-efficient framework. In contrast to previous search algorithms, our method uses a layered circuit structure that significantly reduces the search space. Additionally, our approach can account for multiple objectives such as solution quality, hardware restrictions and circuit depth. We benchmark our tailored circuits against various reference models, including models with problem-agnostic circuits and classical models. Our results highlight the effectiveness of problem-specific encoding circuits in enhancing QML model performance.
Model-based reinforcement learning agents utilizing transformers have shown improved sample efficiency due to their ability to model extended context, resulting in more accurate world models. However, for complex reasoning and planning tasks, these methods primarily rely on continuous representations. This complicates modeling of discrete properties of the real world such as disjoint object classes between which interpolation is not plausible. In this work, we introduce discrete abstract representations for transformer-based learning (DART), a sample-efficient method utilizing discrete representations for modeling both the world and learning behavior. We incorporate a transformer-decoder for auto-regressive world modeling and a transformer-encoder for learning behavior by attending to task-relevant cues in the discrete representation of the world model. For handling partial observability, we aggregate information from past time steps as memory tokens. DART outperforms previous state-of-the-art methods that do not use look-ahead search on the Atari 100k sample efficiency benchmark with a median human-normalized score of 0.790 and beats humans in 9 out of 26 games. We release our code at https://pranaval.github.io/DART/.
This paper investigates a new approach to model-based reinforcement learning using background planning: mixing (approximate) dynamic programming updates and model-free updates, similar to the Dyna architecture. Background planning with learned models is often worse than model-free alternatives, such as Double DQN, even though the former uses significantly more memory and computation. The fundamental problem is that learned models can be inaccurate and often generate invalid states, especially when iterated many steps. In this paper, we avoid this limitation by constraining background planning to a set of (abstract) subgoals and learning only local, subgoal-conditioned models. This goal-space planning (GSP) approach is more computationally efficient, naturally incorporates temporal abstraction for faster long-horizon planning and avoids learning the transition dynamics entirely. We show that our GSP algorithm can propagate value from an abstract space in a manner that helps a variety of base learners learn significantly faster in different domains.