Sampling from Energy-based Policies using Diffusion

Energy-based policies offer a flexible framework for modeling complex, multimodal behaviors in reinforcement learning (RL). In maximum entropy RL, the optimal policy is a Boltzmann distribution derived from the soft Q-function, but direct sampling from this distribution in continuous action spaces is computationally intractable. As a result, existing methods typically use simpler parametric distributions, like Gaussians, for policy representation - limiting their ability to capture the full complexity of multimodal action distributions. In this paper, we introduce a diffusion-based approach for sampling from energy-based policies, where the negative Q-function defines the energy function. Based on this approach, we propose an actor-critic method called Diffusion Q-Sampling (DQS) that enables more expressive policy representations, allowing stable learning in diverse environments. We show that our approach enhances exploration and captures multimodal behavior in continuous control tasks, addressing key limitations of existing methods.

E(3)-Equivariant Mesh Neural Networks

Triangular meshes are widely used to represent three-dimensional objects. As a result, many recent works have address the need for geometric deep learning on 3D mesh. However, we observe that the complexities in many of these architectures does not translate to practical performance, and simple deep models for geometric graphs are competitive in practice. Motivated by this observation, we minimally extend the update equations of E(n)-Equivariant Graph Neural Networks (EGNNs) (Satorras et al., 2021) to incorporate mesh face information, and further improve it to account for long-range interactions through hierarchy. The resulting architecture, Equivariant Mesh Neural Network (EMNN), outperforms other, more complicated equivariant methods on mesh tasks, with a fast run-time and no expensive pre-processing. Our implementation is available at https://github.com/HySonLab/EquiMesh

Iterated Denoising Energy Matching for Sampling from Boltzmann Densities

Efficiently generating statistically independent samples from an unnormalized probability distribution, such as equilibrium samples of many-body systems, is a foundational problem in science. In this paper, we propose Iterated Denoising Energy Matching (iDEM), an iterative algorithm that uses a novel stochastic score matching objective leveraging solely the energy function and its gradient -- and no data samples -- to train a diffusion-based sampler. Specifically, iDEM alternates between (I) sampling regions of high model density from a diffusion-based sampler and (II) using these samples in our stochastic matching objective to further improve the sampler. iDEM is scalable to high dimensions as the inner matching objective, is simulation-free, and requires no MCMC samples. Moreover, by leveraging the fast mode mixing behavior of diffusion, iDEM smooths out the energy landscape enabling efficient exploration and learning of an amortized sampler. We evaluate iDEM on a suite of tasks ranging from standard synthetic energy functions to invariant $n$-body particle systems. We show that the proposed approach achieves state-of-the-art performance on all metrics and trains $2-5\times$ faster, which allows it to be the first method to train using energy on the challenging $55$-particle Lennard-Jones system.

Symmetry Breaking and Equivariant Neural Networks

Using symmetry as an inductive bias in deep learning has been proven to be a principled approach for sample-efficient model design. However, the relationship between symmetry and the imperative for equivariance in neural networks is not always obvious. Here, we analyze a key limitation that arises in equivariant functions: their incapacity to break symmetry at the level of individual data samples. In response, we introduce a novel notion of 'relaxed equivariance' that circumvents this limitation. We further demonstrate how to incorporate this relaxation into equivariant multilayer perceptrons (E-MLPs), offering an alternative to the noise-injection method. The relevance of symmetry breaking is then discussed in various application domains: physics, graph representation learning, combinatorial optimization and equivariant decoding.

Lie Point Symmetry and Physics Informed Networks

Symmetries have been leveraged to improve the generalization of neural networks through different mechanisms from data augmentation to equivariant architectures. However, despite their potential, their integration into neural solvers for partial differential equations (PDEs) remains largely unexplored. We explore the integration of PDE symmetries, known as Lie point symmetries, in a major family of neural solvers known as physics-informed neural networks (PINNs). We propose a loss function that informs the network about Lie point symmetries in the same way that PINN models try to enforce the underlying PDE through a loss function. Intuitively, our symmetry loss ensures that the infinitesimal generators of the Lie group conserve the PDE solutions. Effectively, this means that once the network learns a solution, it also learns the neighbouring solutions generated by Lie point symmetries. Empirical evaluations indicate that the inductive bias introduced by the Lie point symmetries of the PDEs greatly boosts the sample efficiency of PINNs.

Weight-Sharing Regularization

Weight-sharing is ubiquitous in deep learning. Motivated by this, we introduce ''weight-sharing regularization'' for neural networks, defined as $R(w) = \frac{1}{d - 1}\sum_{i > j}^d |w_i - w_j|$. We study the proximal mapping of $R$ and provide an intuitive interpretation of it in terms of a physical system of interacting particles. Using this interpretation, we design a novel parallel algorithm for $\operatorname{prox}_R$ which provides an exponential speedup over previous algorithms, with a depth of $O(\log^3 d)$. Our algorithm makes it feasible to train weight-sharing regularized deep neural networks with proximal gradient descent. Experiments reveal that weight-sharing regularization enables fully-connected networks to learn convolution-like filters.

Learning to Reach Goals via Diffusion

Diffusion models are a powerful class of generative models capable of mapping random noise in high-dimensional spaces to a target manifold through iterative denoising. In this work, we present a novel perspective on goal-conditioned reinforcement learning by framing it within the context of diffusion modeling. Analogous to the diffusion process, where Gaussian noise is used to create random trajectories that walk away from the data manifold, we construct trajectories that move away from potential goal states. We then learn a goal-conditioned policy analogous to the score function. This approach, which we call Merlin, can reach predefined or novel goals from an arbitrary initial state without learning a separate value function. We consider three choices for the noise model to replace Gaussian noise in diffusion - reverse play from the buffer, reverse dynamics model, and a novel non-parametric approach. We theoretically justify our approach and validate it on offline goal-reaching tasks. Empirical results are competitive with state-of-the-art methods, which suggests this perspective on diffusion for RL is a simple, scalable, and effective direction for sequential decision-making.

Equivariant Adaptation of Large Pre-Trained Models

Equivariant networks are specifically designed to ensure consistent behavior with respect to a set of input transformations, leading to higher sample efficiency and more accurate and robust predictions. However, redesigning each component of prevalent deep neural network architectures to achieve chosen equivariance is a difficult problem and can result in a computationally expensive network during both training and inference. A recently proposed alternative towards equivariance that removes the architectural constraints is to use a simple canonicalization network that transforms the input to a canonical form before feeding it to an unconstrained prediction network. We show here that this approach can effectively be used to make a large pre-trained network equivariant. However, we observe that the produced canonical orientations can be misaligned with those of the training distribution, hindering performance. Using dataset-dependent priors to inform the canonicalization function, we are able to make large pre-trained models equivariant while maintaining their performance. This significantly improves the robustness of these models to deterministic transformations of the data, such as rotations. We believe this equivariant adaptation of large pre-trained models can help their domain-specific applications with known symmetry priors.

Using Multiple Vector Channels Improves E(n)-Equivariant Graph Neural Networks

We present a natural extension to E(n)-equivariant graph neural networks that uses multiple equivariant vectors per node. We formulate the extension and show that it improves performance across different physical systems benchmark tasks, with minimal differences in runtime or number of parameters. The proposed multichannel EGNN outperforms the standard singlechannel EGNN on N-body charged particle dynamics, molecular property predictions, and predicting the trajectories of solar system bodies. Given the additional benefits and minimal additional cost of multi-channel EGNN, we suggest that this extension may be of practical use to researchers working in machine learning for the physical sciences

Efficient Dynamics Modeling in Interactive Environments with Koopman Theory

The accurate modeling of dynamics in interactive environments is critical for successful long-range prediction. Such a capability could advance Reinforcement Learning (RL) and Planning algorithms, but achieving it is challenging. Inaccuracies in model estimates can compound, resulting in increased errors over long horizons. We approach this problem from the lens of Koopman theory, where the nonlinear dynamics of the environment can be linearized in a high-dimensional latent space. This allows us to efficiently parallelize the sequential problem of long-range prediction using convolution, while accounting for the agent's action at every time step. Our approach also enables stability analysis and better control over gradients through time. Taken together, these advantages result in significant improvement over the existing approaches, both in the efficiency and the accuracy of modeling dynamics over extended horizons. We also report promising experimental results in dynamics modeling for the scenarios of both model-based planning and model-free RL.