Memory Sequence Length of Data Sampling Impacts the Adaptation of Meta-Reinforcement Learning Agents
This work addresses the problem of improving fast adaptation for embodied agents in real-world scenarios, but it is incremental as it focuses on optimizing data sampling within existing off-policy meta-RL frameworks.
The study investigated how different data sampling strategies, specifically long-memory and short-memory sequence sampling, impact the adaptation and representation capabilities of meta-reinforcement learning agents in unknown environments, finding that a Bayes-optimality-based algorithm showed more robust adaptability than a Thompson sampling-based one, particularly in sparse reward tasks.
Fast adaptation to new tasks is extremely important for embodied agents in the real world. Meta-reinforcement learning (meta-RL) has emerged as an effective method to enable fast adaptation in unknown environments. Compared to on-policy meta-RL algorithms, off-policy algorithms rely heavily on efficient data sampling strategies to extract and represent the historical trajectories. However, little is known about how different data sampling methods impact the ability of meta-RL agents to represent unknown environments. Here, we investigate the impact of data sampling strategies on the exploration and adaptability of meta-RL agents. Specifically, we conducted experiments with two types of off-policy meta-RL algorithms based on Thompson sampling and Bayes-optimality theories in continuous control tasks within the MuJoCo environment and sparse reward navigation tasks. Our analysis revealed the long-memory and short-memory sequence sampling strategies affect the representation and adaptive capabilities of meta-RL agents. We found that the algorithm based on Bayes-optimality theory exhibited more robust and better adaptability than the algorithm based on Thompson sampling, highlighting the importance of appropriate data sampling strategies for the agent's representation of an unknown environment, especially in the case of sparse rewards.