Picture for Cheems Wang

Cheems Wang

Latent Reward: LLM-Empowered Credit Assignment in Episodic Reinforcement Learning

Add code
Dec 15, 2024
Viaarxiv icon

Choices are More Important than Efforts: LLM Enables Efficient Multi-Agent Exploration

Add code
Oct 03, 2024
Figure 1 for Choices are More Important than Efforts: LLM Enables Efficient Multi-Agent Exploration
Figure 2 for Choices are More Important than Efforts: LLM Enables Efficient Multi-Agent Exploration
Figure 3 for Choices are More Important than Efforts: LLM Enables Efficient Multi-Agent Exploration
Figure 4 for Choices are More Important than Efforts: LLM Enables Efficient Multi-Agent Exploration
Viaarxiv icon

Robust Fast Adaptation from Adversarially Explicit Task Distribution Generation

Add code
Jul 28, 2024
Figure 1 for Robust Fast Adaptation from Adversarially Explicit Task Distribution Generation
Figure 2 for Robust Fast Adaptation from Adversarially Explicit Task Distribution Generation
Figure 3 for Robust Fast Adaptation from Adversarially Explicit Task Distribution Generation
Figure 4 for Robust Fast Adaptation from Adversarially Explicit Task Distribution Generation
Viaarxiv icon

Reducing Fine-Tuning Memory Overhead by Approximate and Memory-Sharing Backpropagation

Add code
Jun 24, 2024
Viaarxiv icon

GO4Align: Group Optimization for Multi-Task Alignment

Add code
Apr 09, 2024
Viaarxiv icon