conftrace_

trajectory ranking

5 papers

Explore in graph

Co-occurring keywords

reward learning (68) inverse reinforcement learning (205) llm agent (162) reward extrapolation (3) reward alignment (4) explanation verification (3) black-box representation (1) cooperative learning (65) randomized response (15) reward prediction (16)

Papers

Privacy-Preserving Decentralized Actor-Critic for Cooperative Multi-Agent Reinforcement Learning AISTATS 2024
Prospector: Improving LLM Agents with Self-Asking and Trajectory Ranking EMNLP 2024
Explanation-Guided Reward Alignment IJCAI 2023
Learning Multimodal Rewards from Rankings CORL 2021
Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations ICML 2019