Multi-task Reinforcement Learning with Task Representation Method

Multi-task reinforcement learning (RL) algorithms can train agents to acquire generalized skills across various tasks. However, jointly learning with multiple tasks can induce negative transfer between different tasks, resulting in unstable training. In this paper, we newly propose a task representation method that prevents negative transfer in policy learning. The proposed method for multi-task RL adopts a task embedding network in addition to a policy network, where the policy network takes the output of the task embedding network and states as inputs. Furthermore, we propose a measure of negative transfer and design an overall update method that can minimize the suggested measure. In addition, we raise an issue of the negative effect on soft Q-function learning resulting in unstable Q learning and introduce the clipping method to reduce this issue. The proposed multi-task algorithm is evaluated on various robotics manipulation tasks. Numerical results show that the proposed multi-task RL algorithm effectively minimizes negative transfer and achieves better performance than previous state-of-the-art multi-task RL algorithms.