arXiv subjects

Chao Yu

Publications and source records attributed to Chao Yu.

At least 145 records · Page 8Linked to original sources

arXiv2024

LLM-Powered Hierarchical Language Agent for Real-time Human-AI Coordination

AI agents powered by Large Language Models (LLMs) have made significant advances, enabling them to assist humans in diverse complex tasks and leading to a revolution in human-AI coordination. LLM-powered agents typically require invoking LLM APIs and employing artificially designed complex prompts, which results in high inference latency. While this paradigm works well in scenarios with minimal interactive demands, such as code generation, it is unsuitable for highly interactive and real-time applications, such as gaming. Traditional gaming AI often employs small models or reactive policies, enabling fast inference but offering limited task completion and interaction abilities. In this work, we consider Overcooked as our testbed where players could communicate with natural language and cooperate to serve orders. We propose a Hierarchical Language Agent (HLA) for human-AI coordination that provides both strong reasoning abilities while keeping real-time execution. In particular, HLA adopts a hierarchical framework and comprises three modules: a proficient LLM, referred to as Slow Mind, for intention reasoning and language interaction, a lightweight LLM, referred to as Fast Mind, for generating macro actions, and a reactive policy, referred to as Executor, for transforming macro actions into atomic actions. Human studies show that HLA outperforms other baseline agents, including slow-mind-only agents and fast-mind-only agents, with stronger cooperation abilities, faster responses, and more consistent language communications.

cs.AI↗

arXiv2024

Policy-regularized Offline Multi-objective Reinforcement Learning

In this paper, we aim to utilize only offline trajectory data to train a policy for multi-objective RL. We extend the offline policy-regularized method, a widely-adopted approach for single-objective offline RL problems, into the multi-objective setting in order to achieve the above goal. However, such methods face a new challenge in offline MORL settings, namely the preference-inconsistent demonstration problem. We propose two solutions to this problem: 1) filtering out preference-inconsistent demonstrations via approximating behavior preferences, and 2) adopting regularization techniques with high policy expressiveness. Moreover, we integrate the preference-conditioned scalarized update method into policy-regularized offline RL, in order to simultaneously learn a set of policies using a single policy network, thus reducing the computational cost induced by the training of a large number of individual policies for various preferences. Finally, we introduce Regularization Weight Adaptation to dynamically determine appropriate regularization weights for arbitrary target preferences during deployment. Empirical results on various multi-objective datasets demonstrate the capability of our approach in solving offline MORL problems.

cs.LG↗

arXiv2023

Accelerate Multi-Agent Reinforcement Learning in Zero-Sum Games with Subgame Curriculum Learning

Learning Nash equilibrium (NE) in complex zero-sum games with multi-agent reinforcement learning (MARL) can be extremely computationally expensive. Curriculum learning is an effective way to accelerate learning, but an under-explored dimension for generating a curriculum is the difficulty-to-learn of the subgames -- games induced by starting from a specific state. In this work, we present a novel subgame curriculum learning framework for zero-sum games. It adopts an adaptive initial state distribution by resetting agents to some previously visited states where they can quickly learn to improve performance. Building upon this framework, we derive a subgame selection metric that approximates the squared distance to NE values and further adopt a particle-based state sampler for subgame generation. Integrating these techniques leads to our new algorithm, Subgame Automatic Curriculum Learning (SACL), which is a realization of the subgame curriculum learning framework. SACL can be combined with any MARL algorithm such as MAPPO. Experiments in the particle-world environment and Google Research Football environment show SACL produces much stronger policies than baselines. In the challenging hide-and-seek quadrant environment, SACL produces all four emergent stages and uses only half the samples of MAPPO with self-play. The project website is at https://sites.google.com/view/sacl-rl.

cs.LG↗

arXiv2023

Passive Handwriting Tracking via Weak mmWave Communication Signals

In this letter, a cooperative sensing framework based on millimeter wave (mmWave) communication systems is proposed to detect tiny motions with a millimeter-level resolution. Particularly, the cooperative sensing framework is facilitated with one transmitter and two receivers. There are two radio frequency (RF) chains at each receiver. Hence, the Doppler effect due to the tiny motions can be detected via passive sensing respectively at the receivers, and the velocities of the motions can be estimated by integrating the Doppler frequencies. It is demonstrated that the proposed cooperative sensing system is able to track the handwriting with 90% error below 6 mm. Moreover, the proposed cooperative sensing is robust to the strength of received signal. For example, it works even without the line-of-sight paths from the transmitter to the receivers or the sensing target, where the received signal strength is not sufficient for timing synchronization or demodulation.

eess.SY↗

arXiv2023

Active Neural Topological Mapping for Multi-Agent Exploration

This paper investigates the multi-agent cooperative exploration problem, which requires multiple agents to explore an unseen environment via sensory signals in a limited time. A popular approach to exploration tasks is to combine active mapping with planning. Metric maps capture the details of the spatial representation, but are with high communication traffic and may vary significantly between scenarios, resulting in inferior generalization. Topological maps are a promising alternative as they consist only of nodes and edges with abstract but essential information and are less influenced by the scene structures. However, most existing topology-based exploration tasks utilize classical methods for planning, which are time-consuming and sub-optimal due to their handcrafted design. Deep reinforcement learning (DRL) has shown great potential for learning (near) optimal policies through fast end-to-end inference. In this paper, we propose Multi-Agent Neural Topological Mapping (MANTM) to improve exploration efficiency and generalization for multi-agent exploration tasks. MANTM mainly comprises a Topological Mapper and a novel RL-based Hierarchical Topological Planner (HTP). The Topological Mapper employs a visual encoder and distance-based heuristics to construct a graph containing main nodes and their corresponding ghost nodes. The HTP leverages graph neural networks to capture correlations between agents and graph nodes in a coarse-to-fine manner for effective global goal selection. Extensive experiments conducted in a physically-realistic simulator, Habitat, demonstrate that MANTM reduces the steps by at least 26.40% over planning-based baselines and by at least 7.63% over RL-based competitors in unseen scenarios.

cs.RO↗

arXiv2023

Compact free-running InGaAs/InP single-photon detector with 40% detection efficiency and 2.3 kcps dark count rate

Free-running InGaAs/InP single-photon detectors (SPDs) based on negative-feedback avalanche diodes (NFADs) are the key components for applications requiring asynchronous single-photon detection in the near-infrared region. From the perspective of practical applications, the features of SPDs in terms of high photon detection efficiency (PDE), low noise, large sensitive area, and compactness are highly desired for system integration and performance enhancement. Here, we present the implementation of a compact four-channel multimode fiber coupling free-running InGaAs/InP SPD, with the best overall performance to date. On the one hand, we design and fabricate structure-optimized InGaAs/InP NFAD devices with 25 $μ$m diameter active area and integrated thin film resistors to enhance the maximum achievable PDE. On the other hand, we apply a compact thermoacoustic cryocooler to regulate the operating temperature of NFADs within a large range, and design a dedicated readout circuit with minimized parasitic parameters and tunable settings of hold-off time to suppress the afterpulsing effect. The SPD is then characterized to achieve remarkable overall performance simultaneously at 1550 nm, i.e., 40% PDE, 2.3 kcps dark count rate, 8% afterpulse probability and 49 ps timing jitter (full width at half maximum) under the conditions of 5.9 V excess bias voltage, 10 $μ$s hold-off time and 213 K operation temperature. Such performance and the results of the long-term stability tests indicate that the SPD could be a favorable solution for practical applications.

physics.ins-det↗

arXiv2023

Fictitious Cross-Play: Learning Global Nash Equilibrium in Mixed Cooperative-Competitive Games

Self-play (SP) is a popular multi-agent reinforcement learning (MARL) framework for solving competitive games, where each agent optimizes policy by treating others as part of the environment. Despite the empirical successes, the theoretical properties of SP-based methods are limited to two-player zero-sum games. However, for mixed cooperative-competitive games where agents on the same team need to cooperate with each other, we can show a simple counter-example where SP-based methods cannot converge to a global Nash equilibrium (NE) with high probability. Alternatively, Policy-Space Response Oracles (PSRO) is an iterative framework for learning NE, where the best responses w.r.t. previous policies are learned in each iteration. PSRO can be directly extended to mixed cooperative-competitive settings by jointly learning team best responses with all convergence properties unchanged. However, PSRO requires repeatedly training joint policies from scratch till convergence, which makes it hard to scale to complex games. In this work, we develop a novel algorithm, Fictitious Cross-Play (FXP), which inherits the benefits from both frameworks. FXP simultaneously trains an SP-based main policy and a counter population of best response policies. The main policy is trained by fictitious self-play and cross-play against the counter population, while the counter policies are trained as the best responses to the main policy's past versions. We validate our method in matrix games and show that FXP converges to global NEs while SP methods fail. We also conduct experiments in a gridworld domain, where FXP achieves higher Elo ratings and lower exploitabilities than baselines, and a more challenging football game, where FXP defeats SOTA models with over 94% win rate.

cs.AI↗

arXiv2023

OmniDrones: An Efficient and Flexible Platform for Reinforcement Learning in Drone Control

In this work, we introduce OmniDrones, an efficient and flexible platform tailored for reinforcement learning in drone control, built on Nvidia's Omniverse Isaac Sim. It employs a bottom-up design approach that allows users to easily design and experiment with various application scenarios on top of GPU-parallelized simulations. It also offers a range of benchmark tasks, presenting challenges ranging from single-drone hovering to over-actuated system tracking. In summary, we propose an open-sourced drone simulation platform, equipped with an extensive suite of tools for drone learning. It includes 4 drone models, 5 sensor modalities, 4 control modes, over 10 benchmark tasks, and a selection of widely used RL baselines. To showcase the capabilities of OmniDrones and to support future research, we also provide preliminary results on these benchmark tasks. We hope this platform will encourage further studies on applying RL to practical drone systems.

cs.RO↗

arXiv2023

AlphaZero Gomoku

In the past few years, AlphaZero's exceptional capability in mastering intricate board games has garnered considerable interest. Initially designed for the game of Go, this revolutionary algorithm merges deep learning techniques with the Monte Carlo tree search (MCTS) to surpass earlier top-tier methods. In our study, we broaden the use of AlphaZero to Gomoku, an age-old tactical board game also referred to as "Five in a Row." Intriguingly, Gomoku has innate challenges due to a bias towards the initial player, who has a theoretical advantage. To add value, we strive for a balanced game-play. Our tests demonstrate AlphaZero's versatility in adapting to games other than Go. MCTS has become a predominant algorithm for decision processes in intricate scenarios, especially board games. MCTS creates a search tree by examining potential future actions and uses random sampling to predict possible results. By leveraging the best of both worlds, the AlphaZero technique fuses deep learning from Reinforcement Learning with the balancing act of MCTS, establishing a fresh standard in game-playing AI. Its triumph is notably evident in board games such as Go, chess, and shogi.

cs.AI↗

arXiv2023

Creativity of AI: Hierarchical Planning Model Learning for Facilitating Deep Reinforcement Learning

Despite of achieving great success in real-world applications, Deep Reinforcement Learning (DRL) is still suffering from three critical issues, i.e., data efficiency, lack of the interpretability and transferability. Recent research shows that embedding symbolic knowledge into DRL is promising in addressing those challenges. Inspired by this, we introduce a novel deep reinforcement learning framework with symbolic options. Our framework features a loop training procedure, which enables guiding the improvement of policy by planning with planning models (including action models and hierarchical task network models) and symbolic options learned from interactive trajectories automatically. The learned symbolic options alleviate the dense requirement of expert domain knowledge and provide inherent interpretability of policies. Moreover, the transferability and data efficiency can be further improved by planning with the symbolic planning models. To validate the effectiveness of our framework, we conduct experiments on two domains, Montezuma's Revenge and Office World, respectively. The results demonstrate the comparable performance, improved data efficiency, interpretability and transferability.

cs.AI↗

arXiv2023

Ultraviolet photon-counting single-pixel imaging

We demonstrate photon-counting single-pixel imaging in the ultraviolet region. Toward this target, we develop a high-performance compact single-photon detector based on a 4H-SiC single-photon avalanche diode (SPAD), where a tailored readout circuit with active hold-off time is designed to restrain detector noise and operate the SPAD in free-running mode. We use structured illumination to reconstruct 192$\times$192 compressed images at a 4 fps frame rate. To show the superior capability of ultraviolet characteristics, we use our single-pixel imaging system to identify and distinguish different transparent objects under low-intensity irradiation, and image ultraviolet light sources. The results provide a practical solution for general ultraviolet imaging applications.

physics.optics↗

arXiv2023

Automatic Truss Design with Reinforcement Learning

Truss layout design, namely finding a lightweight truss layout satisfying all the physical constraints, is a fundamental problem in the building industry. Generating the optimal layout is a challenging combinatorial optimization problem, which can be extremely expensive to solve by exhaustive search. Directly applying end-to-end reinforcement learning (RL) methods to truss layout design is infeasible either, since only a tiny portion of the entire layout space is valid under the physical constraints, leading to particularly sparse rewards for RL training. In this paper, we develop AutoTruss, a two-stage framework to efficiently generate both lightweight and valid truss layouts. AutoTruss first adopts Monte Carlo tree search to discover a diverse collection of valid layouts. Then RL is applied to iteratively refine the valid solutions. We conduct experiments and ablation studies in popular truss layout design test cases in both 2D and 3D settings. AutoTruss outperforms the best-reported layouts by 25.1% in the most challenging 3D test cases, resulting in the first effective deep-RL-based approach in the truss layout design literature.

cs.AI↗

arXiv2023

SIFTER: A Task-specific Alignment Strategy for Enhancing Sentence Embeddings

The paradigm of pre-training followed by fine-tuning on downstream tasks has become the mainstream method in natural language processing tasks. Although pre-trained models have the advantage of generalization, their performance may still vary significantly across different domain tasks. This is because the data distribution in different domains varies. For example, the different parts of the sentence 'He married Smt. Dipali Ghosh in 1947 and led a very happy married life' may have different impact for downstream tasks. For similarity calculations, words such as 'led' and 'life' are more important. On the other hand, for sentiment analysis, the word 'happy' is crucial. This indicates that different downstream tasks have different levels of sensitivity to sentence components. Our starting point is to scale information of the model and data according to the specifics of downstream tasks, enhancing domain information of relevant parts for these tasks and reducing irrelevant elements for different domain tasks, called SIFTER. In the experimental part, we use the SIFTER to improve SimCSE by constructing positive sample pairs based on enhancing the sentence stem and reducing the unimportant components in the sentence, and maximize the similarity between three sentences. Similarly, SIFTER can improve the gate mechanism of the LSTM model by short-circuiting the input gate of important words so that the LSTM model remembers the important parts of the sentence. Our experiments demonstrate that SIFTER outperforms the SimCSE and LSTM baselines.

cs.CL↗

arXiv2023

Hierarchical Task Network Planning for Facilitating Cooperative Multi-Agent Reinforcement Learning

Exploring sparse reward multi-agent reinforcement learning (MARL) environments with traps in a collaborative manner is a complex task. Agents typically fail to reach the goal state and fall into traps, which affects the overall performance of the system. To overcome this issue, we present SOMARL, a framework that uses prior knowledge to reduce the exploration space and assist learning. In SOMARL, agents are treated as part of the MARL environment, and symbolic knowledge is embedded using a tree structure to build a knowledge hierarchy. The framework has a two-layer hierarchical structure, comprising a hybrid module with a Hierarchical Task Network (HTN) planning and meta-controller at the higher level, and a MARL-based interactive module at the lower level. The HTN module and meta-controller use Hierarchical Domain Definition Language (HDDL) and the option framework to formalize symbolic knowledge and obtain domain knowledge and a symbolic option set, respectively. Moreover, the HTN module leverages domain knowledge to guide low-level agent exploration by assisting the meta-controller in selecting symbolic options. The meta-controller further computes intrinsic rewards of symbolic options to limit exploration behavior and adjust HTN planning solutions as needed. We evaluate SOMARL on two benchmarks, FindTreasure and MoveBox, and report superior performance over state-of-the-art MARL and subgoal-based baselines for MARL environments significantly.

cs.AI↗

arXiv2023

Causal Deep Reinforcement Learning Using Observational Data

Deep reinforcement learning (DRL) requires the collection of interventional data, which is sometimes expensive and even unethical in the real world, such as in the autonomous driving and the medical field. Offline reinforcement learning promises to alleviate this issue by exploiting the vast amount of observational data available in the real world. However, observational data may mislead the learning agent to undesirable outcomes if the behavior policy that generates the data depends on unobserved random variables (i.e., confounders). In this paper, we propose two deconfounding methods in DRL to address this problem. The methods first calculate the importance degree of different samples based on the causal inference technique, and then adjust the impact of different samples on the loss function by reweighting or resampling the offline dataset to ensure its unbiasedness. These deconfounding methods can be flexibly combined with existing model-free DRL algorithms such as soft actor-critic and deep Q-learning, provided that a weak condition can be satisfied by the loss functions of these algorithms. We prove the effectiveness of our deconfounding methods and validate them experimentally.

cs.LG↗

arXiv2023

Asynchronous Multi-Agent Reinforcement Learning for Efficient Real-Time Multi-Robot Cooperative Exploration

We consider the problem of cooperative exploration where multiple robots need to cooperatively explore an unknown region as fast as possible. Multi-agent reinforcement learning (MARL) has recently become a trending paradigm for solving this challenge. However, existing MARL-based methods adopt action-making steps as the metric for exploration efficiency by assuming all the agents are acting in a fully synchronous manner: i.e., every single agent produces an action simultaneously and every single action is executed instantaneously at each time step. Despite its mathematical simplicity, such a synchronous MARL formulation can be problematic for real-world robotic applications. It can be typical that different robots may take slightly different wall-clock times to accomplish an atomic action or even periodically get lost due to hardware issues. Simply waiting for every robot being ready for the next action can be particularly time-inefficient. Therefore, we propose an asynchronous MARL solution, Asynchronous Coordination Explorer (ACE), to tackle this real-world challenge. We first extend a classical MARL algorithm, multi-agent PPO (MAPPO), to the asynchronous setting and additionally apply action-delay randomization to enforce the learned policy to generalize better to varying action delays in the real world. Moreover, each navigation agent is represented as a team-size-invariant CNN-based policy, which greatly benefits real-robot deployment by handling possible robot lost and allows bandwidth-efficient intra-agent communication through low-dimensional CNN features. We first validate our approach in a grid-based scenario. Both simulation and real-robot results show that ACE reduces over 10% actual exploration time compared with classical approaches. We also apply our framework to a high-fidelity visual-based environment, Habitat, achieving 28% improvement in exploration efficiency.

cs.RO↗

arXiv2023

Models as Agents: Optimizing Multi-Step Predictions of Interactive Local Models in Model-Based Multi-Agent Reinforcement Learning

Research in model-based reinforcement learning has made significant progress in recent years. Compared to single-agent settings, the exponential dimension growth of the joint state-action space in multi-agent systems dramatically increases the complexity of the environment dynamics, which makes it infeasible to learn an accurate global model and thus necessitates the use of agent-wise local models. However, during multi-step model rollouts, the prediction of one local model can affect the predictions of other local models in the next step. As a result, local prediction errors can be propagated to other localities and eventually give rise to considerably large global errors. Furthermore, since the models are generally used to predict for multiple steps, simply minimizing one-step prediction errors regardless of their long-term effect on other models may further aggravate the propagation of local errors. To this end, we propose Models as AGents (MAG), a multi-agent model optimization framework that reversely treats the local models as multi-step decision making agents and the current policies as the dynamics during the model rollout process. In this way, the local models are able to consider the multi-step mutual affect between each other before making predictions. Theoretically, we show that the objective of MAG is approximately equivalent to maximizing a lower bound of the true environment return. Experiments on the challenging StarCraft II benchmark demonstrate the effectiveness of MAG.

cs.MA↗

arXiv2023

mmAlert: mmWave Link Blockage Prediction via Passive Sensing

In this letter, the mmAlert system, predicting millimeter wave (mmWave) link blockage during data communication, is elaborated and demonstrated. The passive sensing method is adopted for mobile blocker detection, where two receive beams with separated radio frequency (RF) chains are equipped at the data communication receiver. One receive beam is aligned to the direction of line-of-sight (LoS) path, and the other one periodically sweeps the region close to the LoS path. By comparing the signals received by the above two beams, the Doppler frequencies of the signal scattered from the mobile blocker can be detected. Furthermore, by tracking the Doppler frequencies and the angle-of-arrivals (AoAs) of the scattered signals, the trajectory of the mobile blocker can be estimated, such that the potential link blockage can be predicted by assuming consistent mobile velocity. It is demonstrated via experiments that the mmAlert system can always detect the motions of the walking person close to the LoS path, and predict 90\% of the LoS blockage with sensing time of 1.4 seconds.

eess.SP↗