NeurIPS 2024 Papers

Multimodal Large Language Models (MLLMs) have demonstrated a wide range of capabilities across many domains including Embodied AI. In this work, we study how to best ground a MLLM into different embodiments and their associated action spaces, including both continuous and discrete actions. For continuous actions, a set of learned tokenizations that capture an action at various resolutions allows for sufficient modeling precision, yielding the best performance on downstream tasks. For discrete actions, semantically aligning these actions with the native output token space of the MLLM leads to the strongest performance. We arrive at these lessons via a thorough study of seven action grounding approaches on five different environments, encompassing over 114 embodied tasks.

In the rapidly evolving domain of vision-based deep reinforcement learning (RL), a pivotal challenge is to achieve generalization capability to dynamic environmental changes reflected in visual observations. Our work delves into the intricacies of this problem, identifying two key issues that appear in previous approaches for visual RL generalization: (i) imbalanced saliency and (ii) observational overfitting. Imbalanced saliency is a phenomenon where an RL agent disproportionately identifies salient features across consecutive frames in a frame stack. Observational overfitting occurs when the agent focuses on certain background regions rather than task-relevant objects. To address these challenges, we present a simple yet effective framework for generalization in visual RL (SimGRL) under dynamic scene perturbations. First, to mitigate the imbalanced saliency problem, we introduce an architectural modification to the image encoder to stack frames at the feature level rather than the image level. Simultaneously, to alleviate the observational overfitting problem, we propose a novel technique called shifted random overlay augmentation, which is specifically designed to learn robust representations capable of effectively handling dynamic visual scenes. Extensive experiments demonstrate the superior generalization capability of SimGRL, achieving state-of-the-art performance in benchmarks including the DeepMind Control Suite.

Masked prediction has emerged as a promising pretraining paradigm in offline reinforcement learning (RL) due to its versatile masking schemes, enabling flexible inference across various downstream tasks with a unified model. Despite the versatility of masked prediction, it remains unclear how to balance the learning of skills at different levels of complexity. To address this, we propose CurrMask, a curriculum masking pretraining paradigm for sequential decision making. Motivated by how humans learn by organizing knowledge in a curriculum, CurrMask adjusts its masking scheme during pretraining for learning versatile skills. Through extensive experiments, we show that CurrMask exhibits superior zero-shot performance on skill prompting tasks, goal-conditioned planning tasks, and competitive finetuning performance on offline RL tasks. Additionally, our analysis of training dynamics reveals that CurrMask gradually acquires skills of varying complexity by dynamically adjusting its masking scheme.

Training agents in multi-agent games presents significant challenges due to their intricate nature. These challenges are exacerbated by dynamics influenced not only by the environment but also by strategies of opponents. Existing methods often struggle with slow convergence and instability. To address these challenges, we harness the potential of imitation learning (IL) to comprehend and anticipate actions of the opponents, aiming to mitigate uncertainties with respect to the game dynamics. Our key contributions include: (i) a new multi-agent IL model for predicting next moves of the opponents - our model works with hidden actions of opponents and local observations; (ii) a new multi-agent reinforcement learning (MARL) algorithm that combines our IL model and policy training into one single training process; and (iii) extensive experiments in three challenging game environments, including an advanced version of the Star-Craft multi-agent challenge (i.e., SMACv2). Experimental results show that our approach achieves superior performance compared to state-of-the-art MARL algorithms.

We study the constant regret guarantees in reinforcement learning (RL). Our objective is to design an algorithm that incurs only finite regret over infinite episodes with high probability. We introduce an algorithm, Cert-LSVI-UCB, for misspecified linear Markov decision processes (MDPs) where both the transition kernel and the reward function can be approximated by some linear function up to misspecification level $\zeta$. At the core of Cert-LSVI-UCB is an innovative certified estimator, which facilitates a fine-grained concentration analysis for multi-phase value-targeted regression, enabling us to establish an instance-dependent regret bound that is constant w.r.t. the number of episodes. Specifically, we demonstrate that for a linear MDP characterized by a minimal suboptimality gap $\Delta$, Cert-LSVI-UCB has a cumulative regret of $\tilde{\mathcal{O}}(d^3H^5/\Delta)$ with high probability, provided that the misspecification level $\zeta$ is below $\tilde{\mathcal{O}}(\Delta / (\sqrt{d}H^2))$. Here $d$ is the dimension of the feature space and $H$ is the horizon. Remarkably, this regret bound is independent of the number of episodes $K$. To the best of our knowledge, Cert-LSVI-UCB is the first algorithm to achieve a constant, instance-dependent, high-probability regret bound in RL with linear function approximation without relying on prior distribution assumptions.