Search Results for author:
Found 45 papers, 23 papers with code
GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-based VLM Agent Training
Reinforcement learning with verifiable outcome rewards (RLVR) has effectively scaled up chain-of-thought (CoT) reasoning in large language models (LLMs).
CORD: Generalizable Cooperation via Role Diversity
To this end, we propose a hierarchical MARL approach to enable generalizable cooperation via role diversity, namely CORD.
Playable Game Generation
In recent years, Artificial Intelligence Generated Content (AIGC) has advanced from text-to-image generation to text-to-video and multimodal video synthesis.
Aligning Few-Step Diffusion Models with Dense Reward Difference Learning
Experimental results demonstrate that SDPO consistently outperforms prior methods in reward-based alignment across diverse step configurations, underscoring its robust step generalization capabilities.
Learning Versatile Skills with Curriculum Masking
Motivated by how humans learn by organizing knowledge in a curriculum, CurrMask adjusts its masking scheme during pretraining for learning versatile skills.
WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents
The resulting world model is composed of the LLM and the learned rules.
Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks
The advancement of Offline Reinforcement Learning (RL) and Offline Multi-Agent Reinforcement Learning (MARL) critically depends on the availability of high-quality, pre-collected offline datasets that represent real-world complexities and practical applications.
A Survey on Self-play Methods in Reinforcement Learning
Self-play, characterized by agents' interactions with copies or past versions of themselves, has recently gained prominence in reinforcement learning (RL).
Multi-agent Reinforcement Learning
reinforcement-learning
+3
Improving Sample Efficiency of Reinforcement Learning with Background Knowledge from Large Language Models
In this paper, we introduce a framework that harnesses LLMs to extract background knowledge of an environment, which contains general understandings of the entire environment, making various downstream RL tasks benefit from one-time knowledge representation.
Reaching Consensus in Cooperative Multi-Agent Reinforcement Learning with Goal Imagination
The common goal is an achievable state with high value, which is obtained by sampling from the distribution of future states.
Affordable Generative Agents
The emergence of large language models (LLMs) has significantly advanced the simulation of believable interactive agents.
More Agents Is All You Need
We find that, simply via a sampling-and-voting method, the performance of large language models (LLMs) scales with the number of agents instantiated.
HGAttack: Transferable Heterogeneous Graph Adversarial Attack
Heterogeneous Graph Neural Networks (HGNNs) are increasingly recognized for their performance in areas like the web and e-commerce, where resilience against adversarial attacks is crucial.
Replay-enhanced Continual Reinforcement Learning
On the other hand, offline learning on replayed tasks while learning a new task may induce a distributional shift between the dataset and the learned policy on old tasks, resulting in forgetting.
LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay
This paper explores the open research problem of understanding the social behaviors of LLM-based agents.
Master-slave Deep Architecture for Top-K Multi-armed Bandits with Non-linear Bandit Feedback and Diversity Constraints
We propose a novel master-slave architecture to solve the top-$K$ combinatorial multi-armed bandits problem with non-linear bandit feedback and diversity constraints, which, to the best of our knowledge, is the first combinatorial bandits setting considering diversity constraints under bandit feedback.
RLTF: Reinforcement Learning from Unit Test Feedback
The goal of program synthesis, or code generation, is to generate executable code based on given descriptions.
Future-conditioned Unsupervised Pretraining for Decision Transformer
While promising, return conditioning is limited to training data labeled with rewards and therefore faces challenges in learning from unsupervised data.
Deploying Offline Reinforcement Learning with Human Feedback
To address this issue, we propose an alternative framework that involves a human supervising the RL models and providing additional feedback in the online deployment phase.
Sample Dropout: A Simple yet Effective Variance Reduction Technique in Deep Policy Optimization
Recent success in Deep Reinforcement Learning (DRL) methods has shown that policy optimization with respect to an off-policy distribution via importance sampling is effective for sample reuse.
Revisiting Estimation Bias in Policy Gradients for Deep Reinforcement Learning
We show that, despite such state distribution shift, the policy gradient estimation bias can be reduced in the following three ways: 1) a small learning rate; 2) an adaptive-learning-rate-based optimizer; and 3) KL regularization.
A Survey on Transformers in Reinforcement Learning
Transformer has been considered the dominating neural architecture in NLP and CV, mostly under supervised settings.
RLogist: Fast Observation Strategy on Whole-slide Images with Deep Reinforcement Learning
Most of the existing methods rely on a multiple instance learning framework that requires densely sampling local patches at high magnification.
Pretraining in Deep Reinforcement Learning: A Survey
The past few years have seen rapid progress in combining reinforcement learning (RL) with deep learning.
Curriculum-based Asymmetric Multi-task Reinforcement Learning
To mitigate the negative influence of customizing the one-off training order in curriculum-based AMTL, CAMRL switches its training mode between parallel single-task RL and asymmetric multi-task RL (MTRL), according to an indicator regarding the training time, the overall performance, and the performance gap among tasks.
More Centralized Training, Still Decentralized Execution: Multi-Agent Conditional Policy Factorization
To this end, we propose multi-agent conditional policy factorization (MACPF), which takes more centralized training but still enables decentralized execution.
Revisiting Discrete Soft Actor-Critic
We study the adaption of Soft Actor-Critic (SAC), which is considered as a state-of-the-art reinforcement learning (RL) algorithm, from continuous action space to discrete action space.
Honor of Kings Arena: an Environment for Generalization in Competitive Reinforcement Learning
Compared to other environments studied in most previous work, ours presents new generalization challenges for competitive reinforcement learning.
Dynamics-Adaptive Continual Reinforcement Learning via Progressive Contextualization
A key challenge of continual reinforcement learning (CRL) in dynamic environments is to promptly adapt the RL agent's behavior as the environment changes over its lifetime, while minimizing the catastrophic forgetting of the learned information.
Quantized Adaptive Subgradient Algorithms and Their Applications
Therefore, a threshold quantization strategy with a relatively small error is adopted in QCMD adagrad and QRDA adagrad to improve the signal-to-noise ratio and preserve the sparsity of the model.
GPN: A Joint Structural Learning Framework for Graph Neural Networks
To the best of our knowledge, our method is the first GNN-based bilevel optimization framework for resolving this task.
MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learned
With this in mind, we hosted the third edition of the MineRL ObtainDiamond competition, MineRL Diamond 2021, with a separate track in which we permitted any solution to promote the participation of newcomers.
JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learning
To address this, we propose JueWu-MC, a sample-efficient hierarchical RL approach equipped with representation learning and imitation learning to deal with perception and exploration.
Efficient Exploration
Hierarchical Reinforcement Learning
+6
Coordinated Proximal Policy Optimization
We present Coordinated Proximal Policy Optimization (CoPPO), an algorithm that extends the original Proximal Policy Optimization (PPO) to the multi-agent setting.
Learning Diverse Policies in MOBA Games via Macro-Goals
Recently, many researchers have made successful progress in building the AI systems for MOBA-game-playing with deep reinforcement learning, such as on Dota 2 and Honor of Kings.
TiKick: Towards Playing Multi-agent Football Full Games from Single-agent Demonstrations
To the best of our knowledge, Tikick is the first learning-based AI system that can take over the multi-agent Google Research Football full game, while previous work could either control a single agent or experiment on toy academic scenarios.
Boosting Offline Reinforcement Learning with Residual Generative Modeling
While most research focuses on the state-action function part through reducing the bootstrapping error in value function approximation induced by the distribution shift of training data, the effects of error propagation in generative modeling have been neglected.
MapGo: Model-Assisted Policy Optimization for Goal-Oriented Tasks
In Goal-oriented Reinforcement learning, relabeling the raw goals in past experience to provide agents with hindsight ability is a major solution to the reward sparsity problem.
Generating Informative CVE Description From ExploitDB Posts by Extractive Summarization
The extracted aspects from an ExploitDB post are then composed into a CVE description according to the suggested CVE description templates, which is must-provided information for requesting new CVEs.
Which Heroes to Pick? Learning to Draft in MOBA Games with Neural Networks and Tree Search
Hero drafting is essential in MOBA game playing as it builds the team of each side and directly affects the match outcome.
Towards Playing Full MOBA Games with Deep Reinforcement Learning
However, existing work falls short in handling the raw game complexity caused by the explosion of agent combinations, i. e., lineups, when expanding the hero pool in case that OpenAI's Dota AI limits the play to a pool of only 17 heroes.
Supervised Learning Achieves Human-Level Performance in MOBA Games: A Case Study of Honor of Kings
Unlike prior attempts, we integrate the macro-strategy and the micromanagement of MOBA-game-playing into neural networks in a supervised and end-to-end manner.
Relation-Aware Transformer for Portfolio Policy Learning
One of the key issues is how to represent the non-stationary price series of assets in a portfolio, which is important for portfolio decisions.
Mastering Complex Control in MOBA Games with Deep Reinforcement Learning
We study the reinforcement learning problem of complex action control in the Multi-player Online Battle Arena (MOBA) 1v1 games.
