Picture for Kosuke Kawakami

Kosuke Kawakami

SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation

Add code
Dec 04, 2023
Viaarxiv icon

Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation

Add code
Dec 04, 2023
Figure 1 for Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation
Figure 2 for Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation
Figure 3 for Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation
Figure 4 for Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation
Viaarxiv icon

Accelerating Offline Reinforcement Learning Application in Real-Time Bidding and Recommendation: Potential Use of Simulation

Add code
Sep 17, 2021
Figure 1 for Accelerating Offline Reinforcement Learning Application in Real-Time Bidding and Recommendation: Potential Use of Simulation
Figure 2 for Accelerating Offline Reinforcement Learning Application in Real-Time Bidding and Recommendation: Potential Use of Simulation
Viaarxiv icon