Training multiple agents to coordinate is an important problem with applications in robotics, game theory, economics, and social sciences. However, most existing Multi-Agent Reinforcement Learning (MARL) methods are online and thus impractical for real-world applications in which collecting new interactions is costly or dangerous. While these algorithms should leverage offline data when available, doing so gives rise to the offline coordination problem. Specifically, we identify and formalize the strategy agreement (SA) and the strategy fine-tuning (SFT) challenges, two coordination issues at which current offline MARL algorithms fail. To address this setback, we propose a simple model-based approach that generates synthetic interaction data and enables agents to converge on a strategy while fine-tuning their policies accordingly. Our resulting method, Model-based Offline Multi-Agent Proximal Policy Optimization (MOMA-PPO), outperforms the prevalent learning methods in challenging offline multi-agent MuJoCo tasks even under severe partial observability and with learned world models.
相關內容
Automaton based approaches have enabled robots to perform various complex tasks. However, most existing automaton based algorithms highly rely on the manually customized representation of states for the considered task, limiting its applicability in deep reinforcement learning algorithms. To address this issue, by incorporating Transformer into reinforcement learning, we develop a Double-Transformer-guided Temporal Logic framework (T2TL) that exploits the structural feature of Transformer twice, i.e., first encoding the LTL instruction via the Transformer module for efficient understanding of task instructions during the training and then encoding the context variable via the Transformer again for improved task performance. Particularly, the LTL instruction is specified by co-safe LTL. As a semantics-preserving rewriting operation, LTL progression is exploited to decompose the complex task into learnable sub-goals, which not only converts non-Markovian reward decision processes to Markovian ones, but also improves the sampling efficiency by simultaneous learning of multiple sub-tasks. An environment-agnostic LTL pre-training scheme is further incorporated to facilitate the learning of the Transformer module resulting in an improved representation of LTL. The simulation results demonstrate the effectiveness of the T2TL framework.
Deep reinforcement learning has achieved significant results in low-level controlling tasks. However, for some applications like autonomous driving and drone flying, it is difficult to control behavior stably since the agent may suddenly change its actions which often lowers the controlling system's efficiency, induces excessive mechanical wear, and causes uncontrollable, dangerous behavior to the vehicle. Recently, a method called conditioning for action policy smoothness (CAPS) was proposed to solve the problem of jerkiness in low-dimensional features for applications such as quadrotor drones. To cope with high-dimensional features, this paper proposes image-based regularization for action smoothness (I-RAS) for solving jerky control in autonomous miniature car racing. We also introduce a control based on impact ratio, an adaptive regularization weight to control the smoothness constraint, called IR control. In the experiment, an agent with I-RAS and IR control significantly improves the success rate from 59% to 95%. In the real-world-track experiment, the agent also outperforms other methods, namely reducing the average finish lap time, while also improving the completion rate even without real world training. This is also justified by an agent based on I-RAS winning the 2022 AWS DeepRacer Final Championship Cup.
We focus on developing efficient and reliable policy optimization strategies for robot learning with real-world data. In recent years, policy gradient methods have emerged as a promising paradigm for training control policies in simulation. However, these approaches often remain too data inefficient or unreliable to train on real robotic hardware. In this paper we introduce a novel policy gradient-based policy optimization framework which systematically leverages a (possibly highly simplified) first-principles model and enables learning precise control policies with limited amounts of real-world data. Our approach $1)$ uses the derivatives of the model to produce sample-efficient estimates of the policy gradient and $2)$ uses the model to design a low-level tracking controller, which is embedded in the policy class. Theoretical analysis provides insight into how the presence of this feedback controller addresses overcomes key limitations of stand-alone policy gradient methods, while hardware experiments with a small car and quadruped demonstrate that our approach can learn precise control strategies reliably and with only minutes of real-world data.
Stable gait generation is a crucial problem for legged robot locomotion as this impacts other critical performance factors such as, e.g. mobility over an uneven terrain and power consumption. Gait generation stability results from the efficient control of the interaction between the legged robot's body and the environment where it moves. Here, we study how this can be achieved by a combination of model-predictive and predictive reinforcement learning controllers. Model-predictive control (MPC) is a well-established method that does not utilize any online learning (except for some adaptive variations) as it provides a convenient interface for state constraints management. Reinforcement learning (RL), in contrast, relies on adaptation based on pure experience. In its bare-bone variants, RL is not always suitable for robots due to their high complexity and expensive simulation/experimentation. In this work, we combine both control methods to address the quadrupedal robot stable gate generation problem. The hybrid approach that we develop and apply uses a cost roll-out algorithm with a tail cost in the form of a Q-function modeled by a neural network; this allows to alleviate the computational complexity, which grows exponentially with the prediction horizon in a purely MPC approach. We demonstrate that our RL gait controller achieves stable locomotion at short horizons, where a nominal MP controller fails. Further, our controller is capable of live operation, meaning that it does not require previous training. Our results suggest that the hybridization of MPC with RL, as presented here, is beneficial to achieve a good balance between online control capabilities and computational complexity.
Offline reinforcement learning (RL) is a promising direction that allows RL agents to pre-train on large datasets, avoiding the recurrence of expensive data collection. To advance the field, it is crucial to generate large-scale datasets. Compositional RL is particularly appealing for generating such large datasets, since 1) it permits creating many tasks from few components, 2) the task structure may enable trained agents to solve new tasks by combining relevant learned components, and 3) the compositional dimensions provide a notion of task relatedness. This paper provides four offline RL datasets for simulated robotic manipulation created using the 256 tasks from CompoSuite [Mendez et al., 2022a]. Each dataset is collected from an agent with a different degree of performance, and consists of 256 million transitions. We provide training and evaluation settings for assessing an agent's ability to learn compositional task policies. Our benchmarking experiments on each setting show that current offline RL methods can learn the training tasks to some extent and that compositional methods significantly outperform non-compositional methods. However, current methods are still unable to extract the tasks' compositional structure to generalize to unseen tasks, showing a need for further research in offline compositional RL.
While deep reinforcement learning (RL) has fueled multiple high-profile successes in machine learning, it is held back from more widespread adoption by its often poor data efficiency and the limited generality of the policies it produces. A promising approach for alleviating these limitations is to cast the development of better RL algorithms as a machine learning problem itself in a process called meta-RL. Meta-RL is most commonly studied in a problem setting where, given a distribution of tasks, the goal is to learn a policy that is capable of adapting to any new task from the task distribution with as little data as possible. In this survey, we describe the meta-RL problem setting in detail as well as its major variations. We discuss how, at a high level, meta-RL research can be clustered based on the presence of a task distribution and the learning budget available for each individual task. Using these clusters, we then survey meta-RL algorithms and applications. We conclude by presenting the open problems on the path to making meta-RL part of the standard toolbox for a deep RL practitioner.
The development of autonomous agents which can interact with other agents to accomplish a given task is a core area of research in artificial intelligence and machine learning. Towards this goal, the Autonomous Agents Research Group develops novel machine learning algorithms for autonomous systems control, with a specific focus on deep reinforcement learning and multi-agent reinforcement learning. Research problems include scalable learning of coordinated agent policies and inter-agent communication; reasoning about the behaviours, goals, and composition of other agents from limited observations; and sample-efficient learning based on intrinsic motivation, curriculum learning, causal inference, and representation learning. This article provides a broad overview of the ongoing research portfolio of the group and discusses open problems for future directions.
We introduce DeepNash, an autonomous agent capable of learning to play the imperfect information game Stratego from scratch, up to a human expert level. Stratego is one of the few iconic board games that Artificial Intelligence (AI) has not yet mastered. This popular game has an enormous game tree on the order of $10^{535}$ nodes, i.e., $10^{175}$ times larger than that of Go. It has the additional complexity of requiring decision-making under imperfect information, similar to Texas hold'em poker, which has a significantly smaller game tree (on the order of $10^{164}$ nodes). Decisions in Stratego are made over a large number of discrete actions with no obvious link between action and outcome. Episodes are long, with often hundreds of moves before a player wins, and situations in Stratego can not easily be broken down into manageably-sized sub-problems as in poker. For these reasons, Stratego has been a grand challenge for the field of AI for decades, and existing AI methods barely reach an amateur level of play. DeepNash uses a game-theoretic, model-free deep reinforcement learning method, without search, that learns to master Stratego via self-play. The Regularised Nash Dynamics (R-NaD) algorithm, a key component of DeepNash, converges to an approximate Nash equilibrium, instead of 'cycling' around it, by directly modifying the underlying multi-agent learning dynamics. DeepNash beats existing state-of-the-art AI methods in Stratego and achieved a yearly (2022) and all-time top-3 rank on the Gravon games platform, competing with human expert players.
Seamlessly interacting with humans or robots is hard because these agents are non-stationary. They update their policy in response to the ego agent's behavior, and the ego agent must anticipate these changes to co-adapt. Inspired by humans, we recognize that robots do not need to explicitly model every low-level action another agent will make; instead, we can capture the latent strategy of other agents through high-level representations. We propose a reinforcement learning-based framework for learning latent representations of an agent's policy, where the ego agent identifies the relationship between its behavior and the other agent's future strategy. The ego agent then leverages these latent dynamics to influence the other agent, purposely guiding them towards policies suitable for co-adaptation. Across several simulated domains and a real-world air hockey game, our approach outperforms the alternatives and learns to influence the other agent.
Recently, deep multiagent reinforcement learning (MARL) has become a highly active research area as many real-world problems can be inherently viewed as multiagent systems. A particularly interesting and widely applicable class of problems is the partially observable cooperative multiagent setting, in which a team of agents learns to coordinate their behaviors conditioning on their private observations and commonly shared global reward signals. One natural solution is to resort to the centralized training and decentralized execution paradigm. During centralized training, one key challenge is the multiagent credit assignment: how to allocate the global rewards for individual agent policies for better coordination towards maximizing system-level's benefits. In this paper, we propose a new method called Q-value Path Decomposition (QPD) to decompose the system's global Q-values into individual agents' Q-values. Unlike previous works which restrict the representation relation of the individual Q-values and the global one, we leverage the integrated gradient attribution technique into deep MARL to directly decompose global Q-values along trajectory paths to assign credits for agents. We evaluate QPD on the challenging StarCraft II micromanagement tasks and show that QPD achieves the state-of-the-art performance in both homogeneous and heterogeneous multiagent scenarios compared with existing cooperative MARL algorithms.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191