Multi-Fidelity Policy Gradient Algorithms

Many reinforcement learning (RL) algorithms require large amounts of data, prohibiting their use in applications where frequent interactions with operational systems are infeasible, or high-fidelity simulations are expensive or unavailable. Meanwhile, low-fidelity simulators--such as reduced-order models, heuristic reward functions, or generative world models--can cheaply provide useful data for RL training, even if they are too coarse for direct sim-to-real transfer. We propose multi-fidelity policy gradients (MFPGs), an RL framework that mixes a small amount of data from the target environment with a large volume of low-fidelity simulation data to form unbiased, reduced-variance estimators (control variates) for on-policy policy gradients. We instantiate the framework by developing multi-fidelity variants of two policy gradient algorithms: REINFORCE and proximal policy optimization. Experimental results across a suite of simulated robotics benchmark problems demonstrate that when target-environment samples are limited, MFPG achieves up to 3.9x higher reward and improves training stability when compared to baselines that only use high-fidelity data. Moreover, even when the baselines are given more high-fidelity samples--up to 10x as many interactions with the target environment--MFPG continues to match or outperform them. Finally, we observe that MFPG is capable of training effective policies even when the low-fidelity environment is drastically different from the target environment. MFPG thus not only offers a novel paradigm for efficient sim-to-real transfer but also provides a principled approach to managing the trade-off between policy performance and data collection costs.

GO: The Great Outdoors Multimodal Dataset

The Great Outdoors (GO) dataset is a multi-modal annotated data resource aimed at advancing ground robotics research in unstructured environments. This dataset provides the most comprehensive set of data modalities and annotations compared to existing off-road datasets. In total, the GO dataset includes six unique sensor types with high-quality semantic annotations and GPS traces to support tasks such as semantic segmentation, object detection, and SLAM. The diverse environmental conditions represented in the dataset present significant real-world challenges that provide opportunities to develop more robust solutions to support the continued advancement of field robotics, autonomous exploration, and perception systems in natural environments. The dataset can be downloaded at: https://www.unmannedlab.org/the-great-outdoors-dataset/

A Multifidelity Sim-to-Real Pipeline for Verifiable and Compositional Reinforcement Learning

We propose and demonstrate a compositional framework for training and verifying reinforcement learning (RL) systems within a multifidelity sim-to-real pipeline, in order to deploy reliable and adaptable RL policies on physical hardware. By decomposing complex robotic tasks into component subtasks and defining mathematical interfaces between them, the framework allows for the independent training and testing of the corresponding subtask policies, while simultaneously providing guarantees on the overall behavior that results from their composition. By verifying the performance of these subtask policies using a multifidelity simulation pipeline, the framework not only allows for efficient RL training, but also for a refinement of the subtasks and their interfaces in response to challenges arising from discrepancies between simulation and reality. In an experimental case study we apply the framework to train and deploy a compositional RL system that successfully pilots a Warthog unmanned ground robot.

A Mapping of Assurance Techniques for Learning Enabled Autonomous Systems to the Systems Engineering Lifecycle

Learning enabled autonomous systems provide increased capabilities compared to traditional systems. However, the complexity of and probabilistic nature in the underlying methods enabling such capabilities present challenges for current systems engineering processes for assurance, and test, evaluation, verification, and validation (TEVV). This paper provides a preliminary attempt to map recently developed technical approaches in the assurance and TEVV of learning enabled autonomous systems (LEAS) literature to a traditional systems engineering v-model. This mapping categorizes such techniques into three main approaches: development, acquisition, and sustainment. We review the latest techniques to develop safe, reliable, and resilient learning enabled autonomous systems, without recommending radical and impractical changes to existing systems engineering processes. By performing this mapping, we seek to assist acquisition professionals by (i) informing comprehensive test and evaluation planning, and (ii) objectively communicating risk to leaders.

Task-Guided IRL in POMDPs that Scales

In inverse reinforcement learning (IRL), a learning agent infers a reward function encoding the underlying task using demonstrations from experts. However, many existing IRL techniques make the often unrealistic assumption that the agent has access to full information about the environment. We remove this assumption by developing an algorithm for IRL in partially observable Markov decision processes (POMDPs). We address two limitations of existing IRL techniques. First, they require an excessive amount of data due to the information asymmetry between the expert and the learner. Second, most of these IRL techniques require solving the computationally intractable forward problem -- computing an optimal policy given a reward function -- in POMDPs. The developed algorithm reduces the information asymmetry while increasing the data efficiency by incorporating task specifications expressed in temporal logic into IRL. Such specifications may be interpreted as side information available to the learner a priori in addition to the demonstrations. Further, the algorithm avoids a common source of algorithmic complexity by building on causal entropy as the measure of the likelihood of the demonstrations as opposed to entropy. Nevertheless, the resulting problem is nonconvex due to the so-called forward problem. We solve the intrinsic nonconvexity of the forward problem in a scalable manner through a sequential linear programming scheme that guarantees to converge to a locally optimal policy. In a series of examples, including experiments in a high-fidelity Unity simulator, we demonstrate that even with a limited amount of data and POMDPs with tens of thousands of states, our algorithm learns reward functions and policies that satisfy the task while inducing similar behavior to the expert by leveraging the provided side information.

Risk Averse Bayesian Reward Learning for Autonomous Navigation from Human Demonstration

Traditional imitation learning provides a set of methods and algorithms to learn a reward function or policy from expert demonstrations. Learning from demonstration has been shown to be advantageous for navigation tasks as it allows for machine learning non-experts to quickly provide information needed to learn complex traversal behaviors. However, a minimal set of demonstrations is unlikely to capture all relevant information needed to achieve the desired behavior in every possible future operational environment. Due to distributional shift among environments, a robot may encounter features that were rarely or never observed during training for which the appropriate reward value is uncertain, leading to undesired outcomes. This paper proposes a Bayesian technique which quantifies uncertainty over the weights of a linear reward function given a dataset of minimal human demonstrations to operate safely in dynamic environments. This uncertainty is quantified and incorporated into a risk averse set of weights used to generate cost maps for planning. Experiments in a 3-D environment with a simulated robot show that our proposed algorithm enables a robot to avoid dangerous terrain completely in two out of three test scenarios and accumulates a lower amount of risk than related approaches in all scenarios without requiring any additional demonstrations.