Autoregressive Transformer models have demonstrated impressive performance in video generation, but their sequential token-by-token decoding process poses a major bottleneck, particularly for long videos represented by tens of thousands of tokens. In this paper, we propose Diagonal Decoding (DiagD), a training-free inference acceleration algorithm for autoregressively pre-trained models that exploits spatial and temporal correlations in videos. Our method generates tokens along diagonal paths in the spatial-temporal token grid, enabling parallel decoding within each frame as well as partially overlapping across consecutive frames. The proposed algorithm is versatile and adaptive to various generative models and tasks, while providing flexible control over the trade-off between inference speed and visual quality. Furthermore, we propose a cost-effective finetuning strategy that aligns the attention patterns of the model with our decoding order, further mitigating the training-inference gap on small-scale models. Experiments on multiple autoregressive video generation models and datasets demonstrate that DiagD achieves up to $10\times$ speedup compared to naive sequential decoding, while maintaining comparable visual fidelity.

The performance of embodied agents has been shown to improve by increasing model parameters, dataset size, and compute. This has been demonstrated in domains from robotics to video games, when generative learning objectives on offline datasets (pre-training) are used to model an agent's behavior (imitation learning) or their environment (world modeling). This paper characterizes the role of scale in these tasks more precisely. Going beyond the simple intuition that `bigger is better', we show that the same types of power laws found in language modeling also arise in world modeling and imitation learning (e.g. between loss and optimal model size). However, the coefficients of these laws are heavily influenced by the tokenizer, task \& architecture -- this has important implications on the optimal sizing of models and data.

Training agents to behave as desired in complex 3D environments from high-dimensional sensory information is challenging. Imitation learning from diverse human behavior provides a scalable approach for training an agent with a sensible behavioral prior, but such an agent may not perform the specific behaviors of interest when deployed. To address this issue, we draw an analogy between the undesirable behaviors of imitation learning agents and the unhelpful responses of unaligned large language models (LLMs). We then investigate how the procedure for aligning LLMs can be applied to aligning agents in a 3D environment from pixels. For our analysis, we utilize an academically illustrative part of a modern console game in which the human behavior distribution is multi-modal, but we want our agent to imitate a single mode of this behavior. We demonstrate that we can align our agent to consistently perform the desired mode, while providing insights and advice for successfully applying this approach to training agents. Project webpage at https://adamjelley.github.io/aligning-agents-like-llms .

Video games have served as useful benchmarks for the decision making community, but going beyond Atari games towards training agents in modern games has been prohibitively expensive for the vast majority of the research community. Recent progress in the research, development and open release of large vision models has the potential to amortize some of these costs across the community. However, it is currently unclear which of these models have learnt representations that retain information critical for sequential decision making. Towards enabling wider participation in the research of gameplaying agents in modern games, we present a systematic study of imitation learning with publicly available visual encoders compared to the typical, task-specific, end-to-end training approach in Minecraft, Minecraft Dungeons and Counter-Strike: Global Offensive. Figure 1: Representative screenshots of all games studied in this paper. However, video games do not only serve as benchmarks but also represent a vast entertainment industry where AI agents may eventually have applications in games development, including game testing or game design (Jacob et al., 2020; Gillberg et al., 2023). In the past, video game research often necessitated close integration with the games themselves to obtain game-specific information and establish a scalable interface for training agents. Work was conducted during an internship at Microsoft Research. To eliminate integration costs during training, we use behavior cloning to train agents entirely offline, utilising previously collected human gameplay data. Although prior research has explored encoding images into lower-dimensional representations for behavior cloning, these studies primarily targeted robotics applications (Nair et al., 2022), where images often resemble real-world scenes. Inspired by the challenges and potential applications in video games, we investigate the following research question: How can images be encoded for data-efficient imitation learning in modern video games? Towards our guiding research question, we compare both end-to-end trained visual encoders and pre-trained visual encoders in three modern video games: Minecraft, Minecraft Dungeons and Counter-Strike: Global Offensive (CS:GO).

Diffusion models have emerged as powerful generative models in the text-toimage domain. This paper studies their application as observation-to-action models for imitating human behaviour in sequential environments. Human behaviour is stochastic and multimodal, with structured correlations between action dimensions. Meanwhile, standard modelling choices in behaviour cloning are limited in their expressiveness and may introduce bias into the cloned policy. We begin by pointing out the limitations of these choices. We then propose that diffusion models are an excellent fit for imitating human behaviour, since they learn an expressive distribution over the joint action space. We introduce several innovations to make diffusion models suitable for sequential environments; designing suitable architectures, investigating the role of guidance, and developing reliable sampling strategies. Experimentally, diffusion models closely match human demonstrations in a simulated robotic control task and a modern 3D gaming environment. To enable Human-AI collaboration, agents must learn to best respond to all plausible human behaviors (Dafoe et al., 2020; Mirsky et al., 2022). In simple environments, it suffices to generate all possible human behaviours (Strouse et al., 2021) but as the complexity of the environment grows this approach will struggle to scale. If we instead assume access to human behavioural data, collaborative agents can be improved by training with models of human behaviour (Carroll et al., 2019). In principle, human behavior can be modelled via imitation learning approaches in which an agent is trained to mimic the actions of a demonstrator from an offline dataset of observation and action tuples. More specifically, Behaviour Cloning (BC), despite being theoretically limited (Ross et al., 2011), has been empirically effective in domains such as autonomous driving (Pomerleau, 1991), robotics (Florence et al., 2022) and game playing (Ye et al., 2020; Pearce and Zhu, 2022). Popular approaches to BC restrict the types of distributions that can be modelled to make learning simpler. A common approach for continuous actions is to learn a point estimate, optimised via Mean Squared Error (MSE), which can be interpereted as an isotropic Gaussian of negligible variance. Another popular approach is to discretise the action space into a finite number of bins and frame as a classification problem. These both suffer due to the approximations they make (illustrated in Figure 1), either encouraging the agent to learn an'average' policy or predicting action dimensions independently resulting in'uncoordinated' behaviour (Ke et al., 2020).

QMIX is a popular $Q$-learning algorithm for cooperative MARL in the centralised training and decentralised execution paradigm. In order to enable easy decentralisation, QMIX restricts the joint action $Q$-values it can represent to be a monotonic mixing of each agent's utilities. However, this restriction prevents it from representing value functions in which an agent's ordering over its actions can depend on other agents' actions. To analyse this representational limitation, we first formalise the objective QMIX optimises, which allows us to view QMIX as an operator that first computes the $Q$-learning targets and then projects them into the space representable by QMIX. This projection returns a representable $Q$-value that minimises the unweighted squared error across all joint actions. We show in particular that this projection can fail to recover the optimal policy even with access to $Q^*$, which primarily stems from the equal weighting placed on each joint action. We rectify this by introducing a weighting into the projection, in order to place more importance on the better joint actions. We propose two weighting schemes and prove that they recover the correct maximal action for any joint action $Q$-values, and therefore for $Q^*$ as well. Based on our analysis and results in the tabular setting, we introduce two scalable versions of our algorithm, Centrally-Weighted (CW) QMIX and Optimistically-Weighted (OW) QMIX and demonstrate improved performance on both predator-prey and challenging multi-agent StarCraft benchmark tasks.

Centralised training with decentralised execution is an important setting for cooperative deep multi-agent reinforcement learning due to communication constraints during execution and computational tractability in training. In this paper, we analyse value-based methods that are known to have superior performance in complex environments [43]. We specifically focus on QMIX [40], the current state-of-the-art in this domain. We show that the representational constraints on the joint action-values introduced by QMIX and similar methods lead to provably poor exploration and suboptimality. Furthermore, we propose a novel approach called MAVEN that hybridises value and policy-based methods by introducing a latent space for hierarchical control. The value-based agents condition their behaviour on the shared latent variable controlled by a hierarchical policy. This allows MAVEN to achieve committed, temporally extended exploration, which is key to solving complex multi-agent tasks. Our experimental results show that MAVEN achieves significant performance improvements on the challenging SMAC domain [43].

This paper investigates the use of intrinsic reward to guide exploration in multi-agent reinforcement learning. We discuss the challenges in applying intrinsic reward to multiple collaborative agents and demonstrate how unreliable reward can prevent decentralized agents from learning the optimal policy. We address this problem with a novel framework, Independent Centrally-assisted Q-learning (ICQL), in which decentralized agents share control and an experience replay buffer with a centralized agent. Only the centralized agent is intrinsically rewarded, but the decentralized agents still benefit from improved exploration, without the distraction of unreliable incentives.

In the last few years, deep multi-agent reinforcement learning (RL) has become a highly active area of research. A particularly challenging class of problems in this area is partially observable, cooperative, multi-agent learning, in which teams of agents must learn to coordinate their behaviour while conditioning only on their private observations. This is an attractive research area since such problems are relevant to a large number of real-world systems and are also more amenable to evaluation than general-sum problems. Standardised environments such as the ALE and MuJoCo have allowed single-agent RL to move beyond toy domains, such as grid worlds. However, there is no comparable benchmark for cooperative multi-agent RL. As a result, most papers in this field use one-off toy problems, making it difficult to measure real progress. In this paper, we propose the StarCraft Multi-Agent Challenge (SMAC) as a benchmark problem to fill this gap. SMAC is based on the popular real-time strategy game StarCraft II and focuses on micromanagement challenges where each unit is controlled by an independent agent that must act based on local observations. We offer a diverse set of challenge maps and recommendations for best practices in benchmarking and evaluations. We also open-source a deep multi-agent RL learning framework including state-of-the-art algorithms. We believe that SMAC can provide a standard benchmark environment for years to come. Videos of our best agents for several SMAC scenarios are available at: https://youtu.be/VZ7zmQ_obZ0.

In many real-world settings, a team of agents must coordinate their behaviour while acting in a decentralised way. At the same time, it is often possible to train the agents in a centralised fashion in a simulated or laboratory setting, where global state information is available and communication constraints are lifted. Learning joint action-values conditioned on extra state information is an attractive way to exploit centralised learning, but the best strategy for then extracting decentralised policies is unclear. Our solution is QMIX, a novel value-based method that can train decentralised policies in a centralised end-to-end fashion. QMIX employs a network that estimates joint action-values as a complex non-linear combination of per-agent values that condition only on local observations. We structurally enforce that the joint-action value is monotonic in the per-agent values, which allows tractable maximisation of the joint action-value in off-policy learning, and guarantees consistency between the centralised and decentralised policies. We evaluate QMIX on a challenging set of StarCraft II micromanagement tasks, and show that QMIX significantly outperforms existing value-based multi-agent reinforcement learning methods.