Abstract
We study ObjectGoal Navigation - where a virtual robot situated in a new environment is asked to navigate to an object. Prior work has shown that imitation learning (IL) on a dataset of human demonstrations achieves promising results. However, this has limitations $-$ 1) IL policies generalize poorly to new states, since the training mimics actions not their consequences, and 2) collecting demonstrations is expensive. On the other hand, reinforcement learning (RL) is trivially scalable, but requires careful reward engineering to achieve desirable behavior. We present a two-stage learning scheme for IL pretraining on human demonstrations followed by RL-finetuning. This leads to a PIRLNav policy that advances the state-of-the-art on ObjectNav from $60.0\%$ success rate to $65.0\%$ ($+5.0\%$ absolute). Using this IL$\rightarrow$RL training recipe, we present a rigorous empirical analysis of design choices. First, we investigate whether human demonstrations can be replaced with `free' (automatically generated) sources of demonstrations, e.g. shortest paths (SP) or task-agnostic frontier exploration (FE) trajectories. We find that IL$\rightarrow$RL on human demonstrations outperforms IL$\rightarrow$RL on SP and FE trajectories, even when controlled for the same IL-pretraining success on TRAIN, and even on a subset of VAL episodes where IL-pretraining success favors the SP or FE policies. Next, we study how RL-finetuning performance scales with the size of the IL pretraining dataset. We find that as we increase the size of the IL-pretraining dataset and get to high IL accuracies, the improvements from RL-finetuning are smaller, and that $90\%$ of the performance of our best IL$\rightarrow$RL policy can be achieved with less than half the number of IL demonstrations. Finally, we analyze failure modes of our ObjectNav policies, and present guidelines for further improving them.
Abstract (translated)
URL
https://arxiv.org/abs/2301.07302
