177 citations · 427 across the 37 of their papers we have counts for
39 papers
Generalized Agent Iteration: One Formal Framework for Iterative Policy Improvement and Recursive Self-Improvement
Hongyao Tang, Yi Ma, Pengyi Li +1
When we speak of recursive self-improvement (RSI), are we speaking of a phenomenon, a mechanism, or a prospect? Towards autonomous and evolving intelligence, RSI is being claimed a…
NoC-Out: A Formally-verified Network-on-Chip Library for Rule-based Hardware Designs
Max Kurze, František Farka, Sebastian Ertel
The Network-on-Chip (NoC) is the communication backbone of any multiprocessor chip. A failure of the NoC has severe consequences for the whole system. Yet, no approach exists that…
Towards a Formal Definition of Agent Memory: Basis, Span, Optimality, and the Sequential Memory Problem
Hongyao Tang
Despite the wide deployment of memory in large-model agents, there is no unified formal account of what a memory is or when it is optimal. This paper takes a first step toward this…
RoboPIN: Grounded Embodied Reasoning via Pinned Chain-of-Thought
Yaoting Huang, Yifu Yuan, Linqi Han +6
Embodied reasoning requires models to perceive task-relevant objects and spaces in physical environments and maintain consistent visual grounding throughout multi-step reasoning. H…
Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models
Yifu Yuan, Yaoting Huang, Xianze Yao +20
We introduce Embodied-R1.5, a unified Embodied Foundation Model (EFM) that integrates comprehensive embodied reasoning capabilities, spanning embodied cognition, task planning, cor…
The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning
Jing Liang, Hongyao Tang, Yi Ma +9
Reinforcement learning (RL) has gained growing attention in large language model (LLM) post-training, yet RL training remains fragile and can suffer from instability or collapse. O…
ForceFlow: Learning to Feel and Act via Contact-Driven Flow Matching
Shuoheng Zhang, Yifu Yuan, Hongyao Tang +7
Existing imitation learning methods enable robots to interact autonomously with the physical environment. However, contact-rich manipulation tasks remain a significant challenge du…
The Rank and Gradient Lost in Non-stationarity: Sample Weight Decay for Mitigating Plasticity Loss in Reinforcement Learning
Zihao Wu, Hongyao Tang, Yi Ma +3
Deep reinforcement learning (RL) suffers from plasticity loss severely due to the nature of non-stationarity, which impairs the ability to adapt to new data and learn continually.…
MUVLA: Learning to Explore Object Navigation via Map Understanding
Peilong Han, Fan Jia, Min Zhang +5
In this paper, we present MUVLA, a Map Understanding Vision-Language-Action model tailored for object navigation. It leverages semantic map abstractions to unify and structure hist…
Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies
Yi Ma, Hongyao Tang, Chenjun Xiao +4
In recent years, the expansion of neural network models and training data has driven remarkable progress in deep learning, particularly in computer vision and natural language proc…
Squeeze the Soaked Sponge: Efficient Off-policy Reinforcement Finetuning for Large Language Model
Jing Liang, Hongyao Tang, Yi Ma +5
Reinforcement Learning (RL) has demonstrated its potential to improve the reasoning ability of Large Language Models (LLMs). One major limitation of most existing Reinforcement Fin…
Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn
Hongyao Tang, Johan Obando-Ceron, Pablo Samuel Castro +2
Plasticity, or the ability of an agent to adapt to new tasks, environments, or distributions, is crucial for continual learning. In this paper, we study the loss of plasticity in d…
Dual Ensembled Multiagent Q-Learning with Hypernet Regularizer
Yaodong Yang, Guangyong Chen, Hongyao Tang +3
Overestimation in single-agent reinforcement learning has been extensively studied. In contrast, overestimation in the multiagent setting has received comparatively little attentio…
Improving Deep Reinforcement Learning by Reducing the Chain Effect of Value and Policy Churn
Hongyao Tang, Glen Berseth
Deep neural networks provide Reinforcement Learning (RL) powerful function approximators to address large-scale decision-making problems. However, these approximators introduce cha…
MFE-ETP: A Comprehensive Evaluation Benchmark for Multi-modal Foundation Models on Embodied Task Planning
Min Zhang, Xian Fu, Jianye Hao +5
In recent years, Multi-modal Foundation Models (MFMs) and Embodied Artificial Intelligence (EAI) have been advancing side by side at an unprecedented pace. The integration of the t…
Bridging Evolutionary Algorithms and Reinforcement Learning: A Comprehensive Survey on Hybrid Algorithms
Pengyi Li, Jianye Hao, Hongyao Tang +3
Evolutionary Reinforcement Learning (ERL), which integrates Evolutionary Algorithms (EAs) and Reinforcement Learning (RL) for optimization, has demonstrated remarkable performance…
The Ladder in Chaos: A Simple and Effective Improvement to General DRL Algorithms by Policy Path Trimming and Boosting
Hongyao Tang, Min Zhang, Jianye Hao
Knowing the learning dynamics of policy is significant to unveiling the mysteries of Reinforcement Learning (RL). It is especially crucial yet challenging to Deep RL, from which th…
State-Aware Proximal Pessimistic Algorithms for Offline Reinforcement Learning
Chen Chen, Hongyao Tang, Yi Ma +4
Pessimism is of great importance in offline reinforcement learning (RL). One broad category of offline RL algorithms fulfills pessimism by explicit or implicit behavior regularizat…
ERL-Re: Efficient Evolutionary Reinforcement Learning with Shared State Representation and Individual Policy Representation
Jianye Hao, Pengyi Li, Hongyao Tang +3
Deep Reinforcement Learning (Deep RL) and Evolutionary Algorithms (EA) are two major paradigms of policy optimization with distinct learning principles, i.e., gradient-based v.s. g…
Towards A Unified Policy Abstraction Theory and Representation Learning Approach in Markov Decision Processes
Min Zhang, Hongyao Tang, Jianye Hao +1
Lying on the heart of intelligent decision-making systems, how policy is represented and optimized is a fundamental problem. The root challenge in this problem is the large scale a…
PAnDR: Fast Adaptation to New Environments from Offline Experiences via Decoupling Policy and Environment Representations
Tong Sang, Hongyao Tang, Yi Ma +5
Deep Reinforcement Learning (DRL) has been a promising solution to many complex decision-making problems. Nevertheless, the notorious weakness in generalization among environments…
PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration
Pengyi Li, Hongyao Tang, Tianpei Yang +8
Learning to collaborate is critical in Multi-Agent Reinforcement Learning (MARL). Previous works promote collaboration by maximizing the correlation of agents' behaviors, which is…
ED2: Environment Dynamics Decomposition World Models for Continuous Control
Jianye Hao, Yifu Yuan, Cong Wang +1
Model-based reinforcement learning (MBRL) achieves significant sample efficiency in practice in comparison to model-free RL, but its performance is often limited by the existence o…
Uncertainty-aware Low-Rank Q-Matrix Estimation for Deep Reinforcement Learning
Tong Sang, Hongyao Tang, Jianye Hao +2
Value estimation is one key problem in Reinforcement Learning. Albeit many successes have been achieved by Deep Reinforcement Learning (DRL) in different fields, the underlying str…