2 papers
cs.LG2023
Diversify & Conquer: Outcome-directed Curriculum RL via Out-of-Distribution Disagreement
Daesol Cho, Seungjae Lee, H. Jin Kim
Reinforcement learning (RL) often faces the challenges of uninformed search problems where the agent should explore without access to the domain knowledge such as characteristics o…
cs.LG2023
Outcome-directed Reinforcement Learning by Uncertainty & Temporal Distance-Aware Curriculum Goal Generation
Daesol Cho, Seungjae Lee, H. Jin Kim
Current reinforcement learning (RL) often suffers when solving a challenging exploration problem where the desired outcomes or high rewards are rarely observed. Even though curricu…