We use cookies to analyze the browsing and usage of our website and to personalize your experience. You can disable these technologies at any time, but this may limit certain functionalities of the site. Read our Privacy Policy for more information.
Setting cookies
You can enable and disable the types of cookies you wish to accept. However certain choices you make could affect the services offered on our sites (e.g. suggestions, personalised ads, etc.).
Essential cookies
These cookies are necessary for the operation of the site and cannot be deactivated. (Still active)
Analytics cookies
Do you accept the use of cookies to measure the audience of our sites?
Multimedia Player
Do you accept the use of cookies to display and allow you to watch the video content hosted by our partners (YouTube, etc.)?
Publications
Boosting Latent Diffusion with Perceptual Objectives
Imitation learning is a data-driven approach to learning policies from expert behavior, but it is prone to unreliable outcomes in out-of-sam… (see more)ple (OOS) regions. While previous research relying on stable dynamical systems guarantees convergence to a desired state, it often overlooks transient behavior. We propose a framework for learning policies using modeled by contractive dynamical systems, ensuring that all policy rollouts converge regardless of perturbations, and in turn, enable efficient OOS recovery. By leveraging recurrent equilibrium networks and coupling layers, the policy structure guarantees contractivity for any parameter choice, which facilitates unconstrained optimization. Furthermore, we provide theoretical upper bounds for worst-case and expected loss terms, rigorously establishing the reliability of our method in deployment. Empirically, we demonstrate substantial OOS performance improvements in robotics manipulation and navigation tasks in simulation.
In the primate neocortex, neurons with similar function are often found to be spatially close. Kohonen's self-organizing map (SOM) has been … (see more)one of the most influential approaches for simulating brain-like topographical organization in artificial neural network models. However, integrating these maps into deep neural networks with multitude of layers has been challenging, with self-organized deep neural networks suffering from substantially diminished capacity to perform visual recognition. We identified a key factor leading to the performance degradation in self-organized topographical neural network models: the discord between predominantly bottom-up learning updates in the self-organizing maps, and those derived from top-down, credit-based learning approaches. To address this, we propose an alternative self organization algorithm, tailored to align with the top-down learning processes in deep neural networks. This model not only emulates critical aspects of cortical topography but also significantly narrows the performance gap between non-topographical and topographical models. This advancement underscores the substantial importance of top-down assigned credits in shaping topographical organization. Our findings are a step in reconciling topographical modeling with the functional efficacy of neural network models, paving the way for more brain-like neural architectures.
The use of deep neural networks in reinforcement learning (RL) often suffers from performance degradation as model size increases. While sof… (see more)t mixtures of experts (SoftMoEs) have recently shown promise in mitigating this issue for online RL, the reasons behind their effectiveness remain largely unknown. In this work we provide an in-depth analysis identifying the key factors driving this performance gain. We discover the surprising result that tokenizing the encoder output, rather than the use of multiple experts, is what is behind the efficacy of SoftMoEs. Indeed, we demonstrate that even with an appropriately scaled single expert, we are able to maintain the performance gains, largely thanks to tokenization.
While one commonly trains large diffusion models by collecting datasets on target downstream tasks, it is often desired to align and finetun… (see more)e pretrained diffusion models on some reward functions that are either designed by experts or learned from small-scale datasets. Existing methods for finetuning diffusion models typically suffer from lack of diversity in generated samples, lack of prior preservation, and/or slow convergence in finetuning. Inspired by recent successes in generative flow networks (GFlowNets), a class of probabilistic models that sample with the unnormalized density of a reward function, we propose a novel GFlowNet method dubbed Nabla-GFlowNet (abbreviated as
Realtime environments change even as agents perform action inference and learning, thus requiring high interaction frequencies to effectivel… (see more)y minimize regret. However, recent advances in machine learning involve larger neural networks with longer inference times, raising questions about their applicability in realtime systems where reaction time is crucial. We present an analysis of lower bounds on regret in realtime reinforcement learning (RL) environments to show that minimizing long-term regret is generally impossible within the typical sequential interaction and learning paradigm, but often becomes possible when sufficient asynchronous compute is available. We propose novel algorithms for staggering asynchronous inference processes to ensure that actions are taken at consistent time intervals, and demonstrate that use of models with high action inference times is only constrained by the environment's effective stochasticity over the inference horizon, and not by action frequency. Our analysis shows that the number of inference processes needed scales linearly with increasing inference times while enabling use of models that are multiple orders of magnitude larger than existing approaches when learning from a realtime simulation of Game Boy games such as Pokémon and Tetris.
We consider fair resource allocation in sequential decision-making environments modeled as weakly coupled Markov decision processes, where r… (see more)esource constraints couple the action spaces of
Natural policy gradient (NPG) is a common policy optimization algorithm and can be viewed as mirror ascent in the space of probabilities. Re… (see more)cently,~\citet{vaswani2021general} introduced a policy gradient method that corresponds to mirror ascent in the dual space of logits. We refine this algorithm, removing its need for a normalization across actions and analyze the resulting method (referred to as SPMA). For tabular MDPs, we prove that SPMA with a constant step-size matches the linear convergence of NPG and achieves a faster convergence than constant step-size (accelerated) softmax policy gradient. To handle large state-action spaces, we extend SPMA to use a log-linear policy parameterization. Unlike that for NPG, generalizing SPMA to the linear function approximation (FA) setting does not require compatible function approximation. Unlike MDPO, a practical generalization of NPG, SPMA with linear FA only requires solving convex softmax classification problems. We prove that SPMA achieves linear convergence to the neighbourhood of the optimal value function. We extend SPMA to handle non-linear FA and evaluate its empirical performance on the MuJoCo and Atari benchmarks. Our results demonstrate that SPMA consistently achieves similar or better performance compared to MDPO, PPO and TRPO.
To achieve state-of-the-art chatbots, large language models are finetuned with reinforcement learning (RL), frequently to optimize human fee… (see more)dback (RLHF). This process is computationally expensive and can take weeks. Offline approaches, like DPO, learn on a static dataset and are efficient but not performant. The dominant paradigm, online and on-policy---synchronously generating from the model, labelling with a reward model, and learning on feedback from the model's own outputs---is performant but not efficient. Following prior work in the generall deep RL setting, we propose separating the actor and learner in RLHF. This enables the asynchronously generation of new samples while learning on prior samples, thus leading to overall faster training and better scaling. But this requires a novel regime for RLHF, online but off-policy: learning on samples from a previous version of our model. We ask a fundamental question: how much off-policyness can we tolerate for asynchronous training to speed up learning but maintain performance? We find that a contrastive loss, Online DPO, is most robust to off-policy data and that robustness increases with the scale of the policy model. We show even further compute optimizations but demonstrate that they come at a performance cost, giving rise to a trade-off. Finally, we verify our design choices by training LLaMA 3.1 8B with RLHF as a helpful chatbot in half the time of a synchronous run while matching final performance.
