Alert button
Picture for Desik Rengarajan

Desik Rengarajan

Alert button

N-Critics: Self-Refinement of Large Language Models with Ensemble of Critics

Nov 08, 2023
Sajad Mousavi, Ricardo Luna Gutiérrez, Desik Rengarajan, Vineet Gundecha, Ashwin Ramesh Babu, Avisek Naug, Antonio Guillen, Soumyendu Sarkar

Viaarxiv icon

Federated Ensemble-Directed Offline Reinforcement Learning

May 04, 2023
Desik Rengarajan, Nitin Ragothaman, Dileep Kalathil, Srinivas Shakkottai

Figure 1 for Federated Ensemble-Directed Offline Reinforcement Learning
Figure 2 for Federated Ensemble-Directed Offline Reinforcement Learning
Figure 3 for Federated Ensemble-Directed Offline Reinforcement Learning
Figure 4 for Federated Ensemble-Directed Offline Reinforcement Learning
Viaarxiv icon

Enhanced Meta Reinforcement Learning using Demonstrations in Sparse Reward Environments

Sep 26, 2022
Desik Rengarajan, Sapana Chaudhary, Jaewon Kim, Dileep Kalathil, Srinivas Shakkottai

Figure 1 for Enhanced Meta Reinforcement Learning using Demonstrations in Sparse Reward Environments
Figure 2 for Enhanced Meta Reinforcement Learning using Demonstrations in Sparse Reward Environments
Figure 3 for Enhanced Meta Reinforcement Learning using Demonstrations in Sparse Reward Environments
Figure 4 for Enhanced Meta Reinforcement Learning using Demonstrations in Sparse Reward Environments
Viaarxiv icon

Reinforcement Learning with Sparse Rewards using Guidance from Offline Demonstration

Feb 13, 2022
Desik Rengarajan, Gargi Vaidya, Akshay Sarvesh, Dileep Kalathil, Srinivas Shakkottai

Figure 1 for Reinforcement Learning with Sparse Rewards using Guidance from Offline Demonstration
Figure 2 for Reinforcement Learning with Sparse Rewards using Guidance from Offline Demonstration
Figure 3 for Reinforcement Learning with Sparse Rewards using Guidance from Offline Demonstration
Figure 4 for Reinforcement Learning with Sparse Rewards using Guidance from Offline Demonstration
Viaarxiv icon

Learning Trembling Hand Perfect Mean Field Equilibrium for Dynamic Mean Field Games

Jun 21, 2020
Kiyeob Lee, Desik Rengarajan, Dileep Kalathil, Srinivas Shakkottai

Figure 1 for Learning Trembling Hand Perfect Mean Field Equilibrium for Dynamic Mean Field Games
Figure 2 for Learning Trembling Hand Perfect Mean Field Equilibrium for Dynamic Mean Field Games
Figure 3 for Learning Trembling Hand Perfect Mean Field Equilibrium for Dynamic Mean Field Games
Figure 4 for Learning Trembling Hand Perfect Mean Field Equilibrium for Dynamic Mean Field Games
Viaarxiv icon

QFlow: A Reinforcement Learning Approach to High QoE Video Streaming over Wireless Networks

Jan 04, 2019
Rajarshi Bhattacharyya, Archana Bura, Desik Rengarajan, Mason Rumuly, Srinivas Shakkottai, Dileep Kalathil, Ricky K. P. Mok, Amogh Dhamdhere

Figure 1 for QFlow: A Reinforcement Learning Approach to High QoE Video Streaming over Wireless Networks
Figure 2 for QFlow: A Reinforcement Learning Approach to High QoE Video Streaming over Wireless Networks
Figure 3 for QFlow: A Reinforcement Learning Approach to High QoE Video Streaming over Wireless Networks
Figure 4 for QFlow: A Reinforcement Learning Approach to High QoE Video Streaming over Wireless Networks
Viaarxiv icon