arXiv subjects

Xiangteng Zhang

Publications and source records attributed to Xiangteng Zhang.

6 recordsLinked to original sources

arXiv2026

On the Identifiability of Controlled World Models

World model serves as a promising tool to infer environment dynamics under high-dimensional observations and candidate actions. Recently, LeCun's JEPA provides a compelling framework for learning such models in representation space. Its action-conditioned extension plays a central role in visual control and latent-space planning, but leaves a fundamental question: can it recover the controlled dynamics from nonlinear observations? This paper presents a joint identifiability condition for controlled world models with Gaussian latent states, which consists of two coupled components: (1) representation identifiability and (2) transition identifiability. The former depends on the spectral separation property while the latter is related to non-degenerate variation of conditional action. We prove that when this condition holds, minimizing the LeJEPA-style predictive objective can recover both latent states and controlled dynamics in the sense of orthogonal transformation. We further prove that the upper bound of transition prediction error is inversely proportional to the spectral separation margin. We also characterize an attainable amplification of counterfactual prediction error that scales inversely with the weakest conditional action-excitation margin. The theoretical predictions are empirically supported across four nonlinear observation settings.

cs.LG↗

arXiv2026

Bootstrap Off-policy with World Model

Online planning has proven effective in reinforcement learning (RL) for improving sample efficiency and final performance. However, using planning for environment interaction inevitably introduces a divergence between the collected data and the policy's actual behaviors, degrading both model learning and policy improvement. To address this, we propose BOOM (Bootstrap Off-policy with WOrld Model), a framework that tightly integrates planning and off-policy learning through a bootstrap loop: the policy initializes the planner, and the planner refines actions to bootstrap the policy through behavior alignment. This loop is supported by a jointly learned world model, which enables the planner to simulate future trajectories and provides value targets to facilitate policy improvement. The core of BOOM is a likelihood-free alignment loss that bootstraps the policy using the planner's non-parametric action distribution, combined with a soft value-weighted mechanism that prioritizes high-return behaviors and mitigates variability in the planner's action quality within the replay buffer. Experiments on the high-dimensional DeepMind Control Suite and Humanoid-Bench show that BOOM achieves state-of-the-art results in both training stability and final performance. The code is accessible at https://github.com/molumitu/BOOM_MBRL.

cs.LG↗

arXiv2025

Off-policy Reinforcement Learning with Model-based Exploration Augmentation

Exploration is fundamental to reinforcement learning (RL), as it determines how effectively an agent discovers and exploits the underlying structure of its environment to achieve optimal performance. Existing exploration methods generally fall into two categories: active exploration and passive exploration. The former introduces stochasticity into the policy but struggles in high-dimensional environments, while the latter adaptively prioritizes transitions in the replay buffer to enhance exploration, yet remains constrained by limited sample diversity. To address the limitation in passive exploration, we propose Modelic Generative Exploration (MoGE), which augments exploration through the generation of under-explored critical states and synthesis of dynamics-consistent experiences through transition models. MoGE is composed of two components: (1) a diffusion-based generator that synthesizes critical states under the guidance of a utility function evaluating each state's potential influence on policy exploration, and (2) a one-step imagination world model for constructing critical transitions based on the critical states for agent learning. Our method adopts a modular formulation that aligns with the principles of off-policy learning, allowing seamless integration with existing algorithms to improve exploration without altering their core structures. Empirical results on OpenAI Gym and DeepMind Control Suite reveal that MoGE effectively bridges exploration and policy learning, leading to remarkable gains in both sample efficiency and performance across complex control tasks.

cs.AI↗

arXiv2024

Conformal Symplectic Optimization for Stable Reinforcement Learning

Training deep reinforcement learning (RL) agents necessitates overcoming the highly unstable nonconvex stochastic optimization inherent in the trial-and-error mechanism. To tackle this challenge, we propose a physics-inspired optimization algorithm called relativistic adaptive gradient descent (RAD), which enhances long-term training stability. By conceptualizing neural network (NN) training as the evolution of a conformal Hamiltonian system, we present a universal framework for transferring long-term stability from conformal symplectic integrators to iterative NN updating rules, where the choice of kinetic energy governs the dynamical properties of resulting optimization algorithms. By utilizing relativistic kinetic energy, RAD incorporates principles from special relativity and limits parameter updates below a finite speed, effectively mitigating abnormal gradient influences. Additionally, RAD models NN optimization as the evolution of a multi-particle system where each trainable parameter acts as an independent particle with an individual adaptive learning rate. We prove RAD's sublinear convergence under general nonconvex settings, where smaller gradient variance and larger batch sizes contribute to tighter convergence. Notably, RAD degrades to the well-known adaptive moment estimation (ADAM) algorithm when its speed coefficient is chosen as one and symplectic factor as a small positive value. Experimental results show RAD outperforming nine baseline optimizers with five RL algorithms across twelve environments, including standard benchmarks and challenging scenarios. Notably, RAD achieves up to a 155.1% performance improvement over ADAM in Atari games, showcasing its efficacy in stabilizing and accelerating RL training.

cs.LG↗

arXiv2021

Feasible Actor-Critic: Constrained Reinforcement Learning for Ensuring Statewise Safety

The safety constraints commonly used by existing safe reinforcement learning (RL) methods are defined only on expectation of initial states, but allow each certain state to be unsafe, which is unsatisfying for real-world safety-critical tasks. In this paper, we introduce the feasible actor-critic (FAC) algorithm, which is the first model-free constrained RL method that considers statewise safety, e.g, safety for each initial state. We claim that some states are inherently unsafe no matter what policy we choose, while for other states there exist policies ensuring safety, where we say such states and policies are feasible. By constructing a statewise Lagrange function available on RL sampling and adopting an additional neural network to approximate the statewise Lagrange multiplier, we manage to obtain the optimal feasible policy which ensures safety for each feasible state and the safest possible policy for infeasible states. Furthermore, the trained multiplier net can indicate whether a given state is feasible or not through the statewise complementary slackness condition. We provide theoretical guarantees that FAC outperforms previous expectation-based constrained RL methods in terms of both constraint satisfaction and reward optimization. Experimental results on both robot locomotive tasks and safe exploration tasks verify the safety enhancement and feasibility interpretation of the proposed method.

cs.LG↗

arXiv2021

Feasibility Enhancement of Constrained Receding Horizon Control Using Generalized Control Barrier Function

Receding horizon control (RHC) is a popular procedure to deal with optimal control problems. Due to the existence of state constraints, optimization-based RHC often suffers the notorious issue of infeasibility, which strongly shrinks the region of controllable state. This paper proposes a generalized control barrier function (CBF) to enlarge the feasible region of constrained RHC with only a one-step constraint on the prediction horizon. This design can reduce the constrained steps by penalizing the tendency to move towards the constraint boundary. Additionally, generalized CBF is able to handle high-order equality or inequality constraints through extending the constrained step to nonadjacent nodes. We apply this technique on an automated vehicle control task. The results show that compared to multi-step pointwise constraints, generalized CBF can effectively avoid the infeasibility issue in a larger partition of the state space, and the computing efficiency is also improved by 14%-23%.

eess.SY↗