Picture for Xiao Qi Shi

Xiao Qi Shi

Information Content Exploration

Add code
Oct 10, 2023
Viaarxiv icon

Scope Loss for Imbalanced Classification and RL Exploration

Add code
Aug 08, 2023
Viaarxiv icon

Energy-based Surprise Minimization for Multi-Agent Value Factorization

Add code
Oct 05, 2020
Figure 1 for Energy-based Surprise Minimization for Multi-Agent Value Factorization
Figure 2 for Energy-based Surprise Minimization for Multi-Agent Value Factorization
Figure 3 for Energy-based Surprise Minimization for Multi-Agent Value Factorization
Figure 4 for Energy-based Surprise Minimization for Multi-Agent Value Factorization
Viaarxiv icon

Evolve To Control: Evolution-based Soft Actor-Critic for Scalable Reinforcement Learning

Add code
Jul 24, 2020
Figure 1 for Evolve To Control: Evolution-based Soft Actor-Critic for Scalable Reinforcement Learning
Figure 2 for Evolve To Control: Evolution-based Soft Actor-Critic for Scalable Reinforcement Learning
Figure 3 for Evolve To Control: Evolution-based Soft Actor-Critic for Scalable Reinforcement Learning
Figure 4 for Evolve To Control: Evolution-based Soft Actor-Critic for Scalable Reinforcement Learning
Viaarxiv icon