Reinforcement learning with Demonstrations from Mismatched Task under Sparse Reward
This work addresses the challenge of transferring demonstrations across similar tasks in robotics, which is incremental but improves efficiency by reducing the need for new data collection for each task.
The paper tackles the problem of sparse rewards in reinforcement learning for robotics by using demonstrations from a mismatched but similar task, proposing a method that shapes rewards using an estimated expert value function and conservatively explores around demonstrations, achieving superior performance over baseline methods in robot manipulation tasks.
Reinforcement learning often suffer from the sparse reward issue in real-world robotics problems. Learning from demonstration (LfD) is an effective way to eliminate this problem, which leverages collected expert data to aid online learning. Prior works often assume that the learning agent and the expert aim to accomplish the same task, which requires collecting new data for every new task. In this paper, we consider the case where the target task is mismatched from but similar with that of the expert. Such setting can be challenging and we found existing LfD methods can not effectively guide learning in mismatched new tasks with sparse rewards. We propose conservative reward shaping from demonstration (CRSfD), which shapes the sparse rewards using estimated expert value function. To accelerate learning processes, CRSfD guides the agent to conservatively explore around demonstrations. Experimental results of robot manipulation tasks show that our approach outperforms baseline LfD methods when transferring demonstrations collected in a single task to other different but similar tasks.