Alert button
Picture for Alec Koppel

Alec Koppel

Alert button

Compressed Online Learning of Conditional Mean Embedding

Add code
Bookmark button
Alert button
May 13, 2024
Boya Hou, Sina Sanjari, Alec Koppel, Subhonmesh Bose

Viaarxiv icon

Global Optimality without Mixing Time Oracles in Average-reward RL via Multi-level Actor-Critic

Add code
Bookmark button
Alert button
Mar 18, 2024
Bhrij Patel, Wesley A. Suttle, Alec Koppel, Vaneet Aggarwal, Brian M. Sadler, Amrit Singh Bedi, Dinesh Manocha

Figure 1 for Global Optimality without Mixing Time Oracles in Average-reward RL via Multi-level Actor-Critic
Figure 2 for Global Optimality without Mixing Time Oracles in Average-reward RL via Multi-level Actor-Critic
Figure 3 for Global Optimality without Mixing Time Oracles in Average-reward RL via Multi-level Actor-Critic
Viaarxiv icon

Independent RL for Cooperative-Competitive Agents: A Mean-Field Perspective

Add code
Bookmark button
Alert button
Mar 17, 2024
Muhammad Aneeq uz Zaman, Alec Koppel, Mathieu Laurière, Tamer Başar

Figure 1 for Independent RL for Cooperative-Competitive Agents: A Mean-Field Perspective
Figure 2 for Independent RL for Cooperative-Competitive Agents: A Mean-Field Perspective
Figure 3 for Independent RL for Cooperative-Competitive Agents: A Mean-Field Perspective
Figure 4 for Independent RL for Cooperative-Competitive Agents: A Mean-Field Perspective
Viaarxiv icon

Beyond Joint Demonstrations: Personalized Expert Guidance for Efficient Multi-Agent Reinforcement Learning

Add code
Bookmark button
Alert button
Mar 13, 2024
Peihong Yu, Manav Mishra, Alec Koppel, Carl Busart, Priya Narayan, Dinesh Manocha, Amrit Bedi, Pratap Tokekar

Figure 1 for Beyond Joint Demonstrations: Personalized Expert Guidance for Efficient Multi-Agent Reinforcement Learning
Figure 2 for Beyond Joint Demonstrations: Personalized Expert Guidance for Efficient Multi-Agent Reinforcement Learning
Figure 3 for Beyond Joint Demonstrations: Personalized Expert Guidance for Efficient Multi-Agent Reinforcement Learning
Figure 4 for Beyond Joint Demonstrations: Personalized Expert Guidance for Efficient Multi-Agent Reinforcement Learning
Viaarxiv icon

MaxMin-RLHF: Towards Equitable Alignment of Large Language Models with Diverse Human Preferences

Add code
Bookmark button
Alert button
Feb 14, 2024
Souradip Chakraborty, Jiahao Qiu, Hui Yuan, Alec Koppel, Furong Huang, Dinesh Manocha, Amrit Singh Bedi, Mengdi Wang

Viaarxiv icon

Near-Optimal Fair Resource Allocation for Strategic Agents without Money: A Data-Driven Approach

Add code
Bookmark button
Alert button
Nov 18, 2023
Sihan Zeng, Sujay Bhatt, Eleonora Kreacic, Parisa Hassanzadeh, Alec Koppel, Sumitra Ganesh

Viaarxiv icon

Byzantine-Resilient Decentralized Multi-Armed Bandits

Add code
Bookmark button
Alert button
Oct 11, 2023
Jingxuan Zhu, Alec Koppel, Alvaro Velasquez, Ji Liu

Figure 1 for Byzantine-Resilient Decentralized Multi-Armed Bandits
Figure 2 for Byzantine-Resilient Decentralized Multi-Armed Bandits
Figure 3 for Byzantine-Resilient Decentralized Multi-Armed Bandits
Figure 4 for Byzantine-Resilient Decentralized Multi-Armed Bandits
Viaarxiv icon

Aligning Agent Policy with Externalities: Reward Design via Bilevel RL

Add code
Bookmark button
Alert button
Aug 03, 2023
Souradip Chakraborty, Amrit Singh Bedi, Alec Koppel, Dinesh Manocha, Huazheng Wang, Furong Huang, Mengdi Wang

Figure 1 for Aligning Agent Policy with Externalities: Reward Design via Bilevel RL
Figure 2 for Aligning Agent Policy with Externalities: Reward Design via Bilevel RL
Figure 3 for Aligning Agent Policy with Externalities: Reward Design via Bilevel RL
Figure 4 for Aligning Agent Policy with Externalities: Reward Design via Bilevel RL
Viaarxiv icon

Limited-Memory Greedy Quasi-Newton Method with Non-asymptotic Superlinear Convergence Rate

Add code
Bookmark button
Alert button
Jun 27, 2023
Zhan Gao, Aryan Mokhtari, Alec Koppel

Figure 1 for Limited-Memory Greedy Quasi-Newton Method with Non-asymptotic Superlinear Convergence Rate
Figure 2 for Limited-Memory Greedy Quasi-Newton Method with Non-asymptotic Superlinear Convergence Rate
Figure 3 for Limited-Memory Greedy Quasi-Newton Method with Non-asymptotic Superlinear Convergence Rate
Figure 4 for Limited-Memory Greedy Quasi-Newton Method with Non-asymptotic Superlinear Convergence Rate
Viaarxiv icon

Ada-NAV: Adaptive Trajectory-Based Sample Efficient Policy Learning for Robotic Navigation

Add code
Bookmark button
Alert button
Jun 09, 2023
Bhrij Patel, Kasun Weerakoon, Wesley A. Suttle, Alec Koppel, Brian M. Sadler, Amrit Singh Bedi, Dinesh Manocha

Figure 1 for Ada-NAV: Adaptive Trajectory-Based Sample Efficient Policy Learning for Robotic Navigation
Figure 2 for Ada-NAV: Adaptive Trajectory-Based Sample Efficient Policy Learning for Robotic Navigation
Figure 3 for Ada-NAV: Adaptive Trajectory-Based Sample Efficient Policy Learning for Robotic Navigation
Figure 4 for Ada-NAV: Adaptive Trajectory-Based Sample Efficient Policy Learning for Robotic Navigation
Viaarxiv icon