Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy

Diplomacy is one of the most sophisticated activities in human society. The complex interactions among multiple parties/ agents involve various abilities like social reasoning, negotiation arts, and long-term strategy planning. Previous AI agents surely have proved their capability of handling multi-step games and larger action spaces on tasks involving multiple agents. However, diplomacy involves a staggering magnitude of decision spaces, especially considering the negotiation stage required. Recently, LLM agents have shown their potential for extending the boundary of previous agents on a couple of applications, however, it is still not enough to handle a very long planning period in a complex multi-agent environment. Empowered with cutting-edge LLM technology, we make the first stab to explore AI's upper bound towards a human-like agent for such a highly comprehensive multi-agent mission by combining three core and essential capabilities for stronger LLM-based societal agents: 1) strategic planner with memory and reflection; 2) goal-oriented negotiate with social reasoning; 3) augmenting memory by self-play games to self-evolving without any human in the loop.

SocialGFs: Learning Social Gradient Fields for Multi-Agent Reinforcement Learning

Multi-agent systems (MAS) need to adaptively cope with dynamic environments, changing agent populations, and diverse tasks. However, most of the multi-agent systems cannot easily handle them, due to the complexity of the state and task space. The social impact theory regards the complex influencing factors as forces acting on an agent, emanating from the environment, other agents, and the agent's intrinsic motivation, referring to the social force. Inspired by this concept, we propose a novel gradient-based state representation for multi-agent reinforcement learning. To non-trivially model the social forces, we further introduce a data-driven method, where we employ denoising score matching to learn the social gradient fields (SocialGFs) from offline samples, e.g., the attractive or repulsive outcomes of each force. During interactions, the agents take actions based on the multi-dimensional gradients to maximize their own rewards. In practice, we integrate SocialGFs into the widely used multi-agent reinforcement learning algorithms, e.g., MAPPO. The empirical results reveal that SocialGFs offer four advantages for multi-agent systems: 1) they can be learned without requiring online interaction, 2) they demonstrate transferability across diverse tasks, 3) they facilitate credit assignment in challenging reward settings, and 4) they are scalable with the increasing number of agents.

Empowering Embodied Visual Tracking with Visual Foundation Models and Offline RL

Embodied visual tracking is to follow a target object in dynamic 3D environments using an agent's egocentric vision. This is a vital and challenging skill for embodied agents. However, existing methods suffer from inefficient training and poor generalization. In this paper, we propose a novel framework that combines visual foundation models (VFM) and offline reinforcement learning (offline RL) to empower embodied visual tracking. We use a pre-trained VFM, such as ``Tracking Anything", to extract semantic segmentation masks with text prompts. We then train a recurrent policy network with offline RL, e.g., Conservative Q-Learning, to learn from the collected demonstrations without online agent-environment interactions. To further improve the robustness and generalization of the policy network, we also introduce a mask re-targeting mechanism and a multi-level data collection strategy. In this way, we can train a robust tracker within an hour on a consumer-level GPU, e.g., Nvidia RTX 3090. Such efficiency is unprecedented for RL-based visual tracking methods. We evaluate our tracker on several high-fidelity environments with challenging situations, such as distraction and occlusion. The results show that our agent outperforms state-of-the-art methods in terms of sample efficiency, robustness to distractors, and generalization to unseen scenarios and targets. We also demonstrate the transferability of the learned tracker from the virtual world to real-world scenarios.

Fast Peer Adaptation with Context-aware Exploration

Fast adapting to unknown peers (partners or opponents) with different strategies is a key challenge in multi-agent games. To do so, it is crucial for the agent to efficiently probe and identify the peer's strategy, as this is the prerequisite for carrying out the best response in adaptation. However, it is difficult to explore the strategies of unknown peers, especially when the games are partially observable and have a long horizon. In this paper, we propose a peer identification reward, which rewards the learning agent based on how well it can identify the behavior pattern of the peer over the historical context, such as the observation over multiple episodes. This reward motivates the agent to learn a context-aware policy for effective exploration and fast adaptation, i.e., to actively seek and collect informative feedback from peers when uncertain about their policies and to exploit the context to perform the best response when confident. We evaluate our method on diverse testbeds that involve competitive (Kuhn Poker), cooperative (PO-Overcooked), or mixed (Predator-Prey-W) games with peer agents. We demonstrate that our method induces more active exploration behavior, achieving faster adaptation and better outcomes than existing methods.

Learning Semantic-Agnostic and Spatial-Aware Representation for Generalizable Visual-Audio Navigation

Visual-audio navigation (VAN) is attracting more and more attention from the robotic community due to its broad applications, \emph{e.g.}, household robots and rescue robots. In this task, an embodied agent must search for and navigate to the sound source with egocentric visual and audio observations. However, the existing methods are limited in two aspects: 1) poor generalization to unheard sound categories; 2) sample inefficient in training. Focusing on these two problems, we propose a brain-inspired plug-and-play method to learn a semantic-agnostic and spatial-aware representation for generalizable visual-audio navigation. We meticulously design two auxiliary tasks for respectively accelerating learning representations with the above-desired characteristics. With these two auxiliary tasks, the agent learns a spatially-correlated representation of visual and audio inputs that can be applied to work on environments with novel sounds and maps. Experiment results on realistic 3D scenes (Replica and Matterport3D) demonstrate that our method achieves better generalization performance when zero-shot transferred to scenes with unseen maps and unheard sound categories.

RSPT: Reconstruct Surroundings and Predict Trajectories for Generalizable Active Object Tracking

Active Object Tracking (AOT) aims to maintain a specific relation between the tracker and object(s) by autonomously controlling the motion system of a tracker given observations. AOT has wide-ranging applications, such as in mobile robots and autonomous driving. However, building a generalizable active tracker that works robustly across different scenarios remains a challenge, especially in unstructured environments with cluttered obstacles and diverse layouts. We argue that constructing a state representation capable of modeling the geometry structure of the surroundings and the dynamics of the target is crucial for achieving this goal. To address this challenge, we present RSPT, a framework that forms a structure-aware motion representation by Reconstructing the Surroundings and Predicting the target Trajectory. Additionally, we enhance the generalization of the policy network by training in an asymmetric dueling mechanism. We evaluate RSPT on various simulated scenarios and show that it outperforms existing methods in unseen environments, particularly those with complex obstacles and layouts. We also demonstrate the successful transfer of RSPT to real-world settings. Project Website: https://sites.google.com/view/aot-rspt.

Proactive Multi-Camera Collaboration For 3D Human Pose Estimation

This paper presents a multi-agent reinforcement learning (MARL) scheme for proactive Multi-Camera Collaboration in 3D Human Pose Estimation in dynamic human crowds. Traditional fixed-viewpoint multi-camera solutions for human motion capture (MoCap) are limited in capture space and susceptible to dynamic occlusions. Active camera approaches proactively control camera poses to find optimal viewpoints for 3D reconstruction. However, current methods still face challenges with credit assignment and environment dynamics. To address these issues, our proposed method introduces a novel Collaborative Triangulation Contribution Reward (CTCR) that improves convergence and alleviates multi-agent credit assignment issues resulting from using 3D reconstruction accuracy as the shared reward. Additionally, we jointly train our model with multiple world dynamics learning tasks to better capture environment dynamics and encourage anticipatory behaviors for occlusion avoidance. We evaluate our proposed method in four photo-realistic UE4 environments to ensure validity and generalizability. Empirical results show that our method outperforms fixed and active baselines in various scenarios with different numbers of cameras and humans.

GFPose: Learning 3D Human Pose Prior with Gradient Fields

Learning 3D human pose prior is essential to human-centered AI. Here, we present GFPose, a versatile framework to model plausible 3D human poses for various applications. At the core of GFPose is a time-dependent score network, which estimates the gradient on each body joint and progressively denoises the perturbed 3D human pose to match a given task specification. During the denoising process, GFPose implicitly incorporates pose priors in gradients and unifies various discriminative and generative tasks in an elegant framework. Despite the simplicity, GFPose demonstrates great potential in several downstream tasks. Our experiments empirically show that 1) as a multi-hypothesis pose estimator, GFPose outperforms existing SOTAs by 20% on Human3.6M dataset. 2) as a single-hypothesis pose estimator, GFPose achieves comparable results to deterministic SOTAs, even with a vanilla backbone. 3) GFPose is able to produce diverse and realistic samples in pose denoising, completion and generation tasks. Project page https://sites.google.com/view/gfpose/

TarGF: Learning Target Gradient Field for Object Rearrangement

Object Rearrangement is to move objects from an initial state to a goal state. Here, we focus on a more practical setting in object rearrangement, i.e., rearranging objects from shuffled layouts to a normative target distribution without explicit goal specification. However, it remains challenging for AI agents, as it is hard to describe the target distribution (goal specification) for reward engineering or collect expert trajectories as demonstrations. Hence, it is infeasible to directly employ reinforcement learning or imitation learning algorithms to address the task. This paper aims to search for a policy only with a set of examples from a target distribution instead of a handcrafted reward function. We employ the score-matching objective to train a Target Gradient Field (TarGF), indicating a direction on each object to increase the likelihood of the target distribution. For object rearrangement, the TarGF can be used in two ways: 1) For model-based planning, we can cast the target gradient into a reference control and output actions with a distributed path planner; 2) For model-free reinforcement learning, the TarGF is not only used for estimating the likelihood-change as a reward but also provides suggested actions in residual policy learning. Experimental results in ball rearrangement and room rearrangement demonstrate that our method significantly outperforms the state-of-the-art methods in the quality of the terminal state, the efficiency of the control process, and scalability. The code and demo videos are on our project website.

GraspARL: Dynamic Grasping via Adversarial Reinforcement Learning

Grasping moving objects, such as goods on a belt or living animals, is an important but challenging task in robotics. Conventional approaches rely on a set of manually defined object motion patterns for training, resulting in poor generalization to unseen object trajectories. In this work, we introduce an adversarial reinforcement learning framework for dynamic grasping, namely GraspARL. To be specific. we formulate the dynamic grasping problem as a 'move-and-grasp' game, where the robot is to pick up the object on the mover and the adversarial mover is to find a path to escape it. Hence, the two agents play a min-max game and are trained by reinforcement learning. In this way, the mover can auto-generate diverse moving trajectories while training. And the robot trained with the adversarial trajectories can generalize to various motion patterns. Empirical results on the simulator and real-world scenario demonstrate the effectiveness of each and good generalization of our method.