RL problems through the idea of "learning to learn". Current meta-RL methods can be classified in to two categories. These methods mainly differ in their ways of inference [3, 4, 20]. The other line follows the technique of relabeling that enables sample reuse across tasks, i.e., learning a task Packer et al. apply hindsight relabeling for meta-RL, and propose hindsight task relabeling (HTR) to relabel the trajectories Taking a step further than hindsight relabelling, Wan et al. introduce additionally foresight Huang et al. derive a general form of policy gradient from DR value estimator [29], whereas a DR off-policy actor-critic Kallus et al. propose the doubly robust method to find a robust policy that can Depending on the knowledge to be transferred, these methods in RL can be roughly divided into classes including sampled transitions [32, 33], learned policies or value networks [34, 35, 36, 37], features [38, 39, 40], and skills [41, 42]. Doubly Robust Property for Direct Use of Doubly Robust Estimator We show the doubly robust property of the DR estimator for value function in Eq. (5) in the main text, as follows.

Meta-reinforcement learning (Meta-RL), though enabling a fast adaptation to learn new skills by exploiting the common structure shared among different tasks, suffers performance degradation in the sparse-reward setting. Current hindsight-based sample transfer approaches can alleviate this issue by transferring relabeled trajectories from other tasks to a new task so as to provide informative experience for the target reward function, but are unfortunately constrained with the unrealistic assumption that tasks differ only in reward functions. In this paper, we propose a doubly robust augmented transfer (DRaT) approach, aiming at addressing the more general sparse reward meta-RL scenario with both dynamics mismatches and varying reward functions across tasks. Specifically, we design a doubly robust augmented estimator for efficient value-function evaluation, which tackles dynamics mismatches with the optimal importance weight of transition distributions achieved by minimizing the theoretically derived upper bound of mean squared error (MSE) between the estimated values of transferred samples and their true values in the target task. Due to its intractability, we then propose an interval-based approximation to this optimal importance weight, which is guaranteed to cover the optimum with a constrained and sample-independent upper bound on the MSE approximation error. Based on our theoretical findings, we finally develop a DRaT algorithm for transferring informative samples across tasks during the training of meta-RL. We implement DRaT on an off-policy meta-RL baseline, and empirically show that it significantly outperforms other hindsight-based approaches on various sparse-reward MuJoCo locomotion tasks with varying dynamics and reward functions.

RL problems through the idea of "learning to learn". Current meta-RL methods can be classified in to two categories. These methods mainly differ in their ways of inference [3, 4, 20]. The other line follows the technique of relabeling that enables sample reuse across tasks, i.e., learning a task Packer et al. apply hindsight relabeling for meta-RL, and propose hindsight task relabeling (HTR) to relabel the trajectories Taking a step further than hindsight relabelling, Wan et al. introduce additionally foresight Huang et al. derive a general form of policy gradient from DR value estimator [29], whereas a DR off-policy actor-critic Kallus et al. propose the doubly robust method to find a robust policy that can Depending on the knowledge to be transferred, these methods in RL can be roughly divided into classes including sampled transitions [32, 33], learned policies or value networks [34, 35, 36, 37], features [38, 39, 40], and skills [41, 42]. Doubly Robust Property for Direct Use of Doubly Robust Estimator We show the doubly robust property of the DR estimator for value function in Eq. (5) in the main text, as follows.

Meta-reinforcement learning (Meta-RL), though enabling a fast adaptation to learn new skills by exploiting the common structure shared among different tasks, suffers performance degradation in the sparse-reward setting. Current hindsight-based sample transfer approaches can alleviate this issue by transferring relabeled trajectories from other tasks to a new task so as to provide informative experience for the target reward function, but are unfortunately constrained with the unrealistic assumption that tasks differ only in reward functions. In this paper, we propose a doubly robust augmented transfer (DRaT) approach, aiming at addressing the more general sparse reward meta-RL scenario with both dynamics mismatches and varying reward functions across tasks. Specifically, we design a doubly robust augmented estimator for efficient value-function evaluation, which tackles dynamics mismatches with the optimal importance weight of transition distributions achieved by minimizing the theoretically derived upper bound of mean squared error (MSE) between the estimated values of transferred samples and their true values in the target task. Due to its intractability, we then propose an interval-based approximation to this optimal importance weight, which is guaranteed to cover the optimum with a constrained and sample-independent upper bound on the MSE approximation error.