25 citations · 82 across the 21 of their papers we have counts for
4 papers · 1 filter
Uncertainty-driven Trajectory Truncation for Data Augmentation in Offline Reinforcement Learning
Junjie Zhang, Jiafei Lyu, Xiaoteng Ma +4
Equipped with the trained environmental dynamics, model-based offline reinforcement learning (RL) algorithms can often successfully learn good policies from fixed-sized datasets, e…
Value Activation for Bias Alleviation: Generalized-activated Deep Double Deterministic Policy Gradients
Jiafei Lyu, Yu Yang, Jiangpeng Yan +1
It is vital to accurately estimate the value function in Deep Reinforcement Learning (DRL) such that the agent could execute proper actions instead of suboptimal ones. However, exi…
Efficient Continuous Control with Double Actors and Regularized Critics
Jiafei Lyu, Xiaoteng Ma, Jiangpeng Yan +1
How to obtain good value estimation is one of the key problems in Reinforcement Learning (RL). Current value estimation methods, such as DDPG and TD3, suffer from unnecessary over-…
Bias-reduced Multi-step Hindsight Experience Replay for Efficient Multi-goal Reinforcement Learning
Rui Yang, Jiafei Lyu, Yu Yang +5
Multi-goal reinforcement learning is widely applied in planning and robot manipulation. Two main challenges in multi-goal reinforcement learning are sparse rewards and sample ineff…