Learning task-relevant representations via rewards and real actions for reinforcement learning
L Yuan, X Lu, Y Liu - Knowledge-Based Systems, 2024 - Elsevier
The input of visual reinforcement learning often contains redundant information, which will
reduce the decision efficiency and decrease the performance of the agent. To address this …
reduce the decision efficiency and decrease the performance of the agent. To address this …
Learning Task-relevant Sequence Representations via Intrinsic Dynamics Characteristics in Reinforcement Learning
D Liang, J Lai, Y Liu - arXiv preprint arXiv:2405.19736, 2024 - arxiv.org
Learning task-relevant state representations is crucial to solving the problem of scene
generalization in visual deep reinforcement learning. Prior work typically establishes a self …
generalization in visual deep reinforcement learning. Prior work typically establishes a self …