Picture for Thomas Carta

Thomas Carta

Reinforcement Learning for Aligning Large Language Models Agents with Interactive Environments: Quantifying and Mitigating Prompt Overfitting

Add code
Oct 29, 2024
Viaarxiv icon

SAC-GLAM: Improving Online RL for LLM agents with Soft Actor-Critic and Hindsight Relabeling

Add code
Oct 16, 2024
Figure 1 for SAC-GLAM: Improving Online RL for LLM agents with Soft Actor-Critic and Hindsight Relabeling
Figure 2 for SAC-GLAM: Improving Online RL for LLM agents with Soft Actor-Critic and Hindsight Relabeling
Figure 3 for SAC-GLAM: Improving Online RL for LLM agents with Soft Actor-Critic and Hindsight Relabeling
Figure 4 for SAC-GLAM: Improving Online RL for LLM agents with Soft Actor-Critic and Hindsight Relabeling
Viaarxiv icon

Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning

Add code
Feb 06, 2023
Viaarxiv icon

EAGER: Asking and Answering Questions for Automatic Reward Shaping in Language-guided RL

Add code
Jun 20, 2022
Figure 1 for EAGER: Asking and Answering Questions for Automatic Reward Shaping in Language-guided RL
Figure 2 for EAGER: Asking and Answering Questions for Automatic Reward Shaping in Language-guided RL
Figure 3 for EAGER: Asking and Answering Questions for Automatic Reward Shaping in Language-guided RL
Figure 4 for EAGER: Asking and Answering Questions for Automatic Reward Shaping in Language-guided RL
Viaarxiv icon

VisualHints: A Visual-Lingual Environment for Multimodal Reinforcement Learning

Add code
Oct 26, 2020
Figure 1 for VisualHints: A Visual-Lingual Environment for Multimodal Reinforcement Learning
Figure 2 for VisualHints: A Visual-Lingual Environment for Multimodal Reinforcement Learning
Figure 3 for VisualHints: A Visual-Lingual Environment for Multimodal Reinforcement Learning
Figure 4 for VisualHints: A Visual-Lingual Environment for Multimodal Reinforcement Learning
Viaarxiv icon