Picture for Kuo-Hao Ho

Kuo-Hao Ho

PPO-Clip Attains Global Optimality: Towards Deeper Understandings of Clipping

Add code
Dec 19, 2023
Viaarxiv icon

Residual Scheduling: A New Reinforcement Learning Approach to Solving Job Shop Scheduling Problem

Add code
Oct 03, 2023
Viaarxiv icon

Towards Human-Like RL: Taming Non-Naturalistic Behavior in Deep RL via Adaptive Behavioral Costs in 3D Games

Add code
Sep 27, 2023
Viaarxiv icon

Hinge Policy Optimization: Rethinking Policy Improvement and Reinterpreting PPO

Add code
Oct 26, 2021
Figure 1 for Hinge Policy Optimization: Rethinking Policy Improvement and Reinterpreting PPO
Figure 2 for Hinge Policy Optimization: Rethinking Policy Improvement and Reinterpreting PPO
Figure 3 for Hinge Policy Optimization: Rethinking Policy Improvement and Reinterpreting PPO
Viaarxiv icon