Pengyi Li
11 papers · 2022–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π Cross-Pollinator (14) π Conference Polyglot (4) πΊοΈ Taxonomy Completionist (16) π Interdisciplinary Bridge π§ Keyword Pioneer
π€
Dynamic Duo
(10)
π
Triple Crown
π₯
Unstoppable
(5)
π
Century Club
(11)
β‘
Prolific Year
(5)
Conferences
ICML (5)
ICLR (3)
NIPS (2)
WACV (1)
Top co-authors
Keywords
multi-agent reinforcement learning
(2)
reinforcement learning
(2)
model-based planning
(1)
representation learning
(1)
policy optimization
(1)
decision making
(1)
policy learning
(1)
video understanding
(1)
progressive learning
(1)
mutual information
(1)
generative model
(1)
diffusion model
(1)
policy exploration
(1)
planning algorithm
(1)
evolutionary algorithm
(1)
trajectory generation
(1)
modular library
(1)
algorithm implementation
(1)
frame sampling
(1)
video large language model
(1)
Papers
MaxInfo: A Training-Free Key-Frame Selection Method Using Maximum Volume for Enhanced Video Understanding
WACV 2026
R*: Efficient Reward Design via Reward Structure Evolution and Parameter Alignment Optimization with Large Language Models
ICML 2025
Sample-Efficient Quality-Diversity by Cooperative Coevolution
ICLR 2024
CleanDiffuser: An Easy-to-use Modularized Library for Diffusion Models in Decision Making
NIPS 2024
DiffuserLite: Towards Real-time Diffusion Planning
NIPS 2024
Value-Evolutionary-Based Reinforcement Learning
ICML 2024
EvoRainbow: Combining Improvements in Evolutionary Reinforcement Learning for Policy Search
ICML 2024
ERL-Re$^2$: Efficient Evolutionary Reinforcement Learning with Shared State Representation and Individual Policy Representation
ICLR 2023
RACE: Improve Multi-Agent Reinforcement Learning with Representation Asymmetry and Collaborative Evolution
ICML 2023
HyAR: Addressing Discrete-Continuous Action Reinforcement Learning via Hybrid Action Representation
ICLR 2022
PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration
ICML 2022