Model-free reinforcement learning (RL) for legged locomotion commonly relies on a physics simulator that can accurately predict the behaviors of every degree of freedom of the robot. In contrast, approximate reduced-order models are often sufficient for many model-based control strategies. In this work we explore how RL can be effectively used with a centroidal model to generate robust control policies for quadrupedal locomotion. Advantages over RL with a full-order model include a simple reward structure, reduced computational costs, and robust sim-to-real transfer. We further show the potential of the method by demonstrating stepping-stone locomotion, two-legged in-place balance, balance beam locomotion, and sim-to-real transfer without further adaptations. Additional Results: https://www.pair.toronto.edu/glide-quadruped/.
The process of learning a manipulation task depends strongly on the action space used for exploration: posed in the incorrect action space, solving a task with reinforcement learning can be drastically inefficient. Additionally, similar tasks or instances of the same task family impose latent manifold constraints on the most effective action space: the task family can be best solved with actions in a manifold of the entire action space of the robot. Combining these insights we present LASER, a method to learn latent action spaces for efficient reinforcement learning. LASER factorizes the learning problem into two sub-problems, namely action space learning and policy learning in the new action space. It leverages data from similar manipulation task instances, either from an offline expert or online during policy learning, and learns from these trajectories a mapping from the original to a latent action space. LASER is trained as a variational encoder-decoder model to map raw actions into a disentangled latent action space while maintaining action reconstruction and latent space dynamic consistency. We evaluate LASER on two contact-rich robotic tasks in simulation, and analyze the benefit of policy learning in the generated latent action space. We show improved sample efficiency compared to the original action space from better alignment of the action space to the task space, as we observe with visualizations of the learned action space manifold. Additional details: https://www.pair.toronto.edu/laser
A kitchen assistant needs to operate human-scale objects, such as cabinets and ovens, in unmapped environments with dynamic obstacles. Autonomous interactions in such real-world environments require integrating dexterous manipulation and fluid mobility. While mobile manipulators in different form-factors provide an extended workspace, their real-world adoption has been limited. This limitation is in part due to two main reasons: 1) inability to interact with unknown human-scale objects such as cabinets and ovens, and 2) inefficient coordination between the arm and the mobile base. Executing a high-level task for general objects requires a perceptual understanding of the object as well as adaptive whole-body control among dynamic obstacles. In this paper, we propose a two-stage architecture for autonomous interaction with large articulated objects in unknown environments. The first stage uses a learned model to estimate the articulated model of a target object from an RGB-D input and predicts an action-conditional sequence of states for interaction. The second stage comprises of a whole-body motion controller to manipulate the object along the generated kinematic plan. We show that our proposed pipeline can handle complicated static and dynamic kitchen settings. Moreover, we demonstrate that the proposed approach achieves better performance than commonly used control methods in mobile manipulation. For additional material, please check: https://www.pair.toronto.edu/articulated-mm/ .
Offline reinforcement learning proposes to learn policies from large collected datasets without interaction. These algorithms have made it possible to learn useful skills from data that can then be transferred to the environment, making it feasible to deploy the trained policies in real-world settings where interactions may be costly or dangerous, such as self-driving. However, current algorithms overfit to the dataset they are trained on and perform poor out-of-distribution (OOD) generalization to the environment when deployed. We propose a Surprisingly Simple Self-Supervision algorithm (S4RL), which utilizes data augmentations from states to learn value functions that are better at generalizing and extrapolating when deployed in the environment. We investigate different data augmentation techniques that help learning a value function that can extrapolate to OOD data, and how to combine data augmentations and offline RL algorithms to learn a policy. We experimentally show that using S4RL significantly improves the state-of-the-art on most benchmark offline reinforcement learning tasks on popular benchmark datasets from D4RL, despite being simple and easy to implement.
We present an approach for physical imitation from human videos for robot manipulation tasks. The key idea of our method lies in explicitly exploiting the kinematics and motion information embedded in the video to learn structured representations that endow the robot with the ability to imagine how to perform manipulation tasks in its own context. To achieve this, we design a perception module that learns to translate human videos to the robot domain followed by unsupervised keypoint detection. The resulting keypoint-based representations provide semantically meaningful information that can be directly used for reward computing and policy learning. We evaluate the effectiveness of our approach on five robot manipulation tasks, including reaching, pushing, sliding, coffee making, and drawer closing. Detailed experimental evaluations demonstrate that our method performs favorably against previous approaches.
Evolution in nature illustrates that the creatures' biological structure and their sensorimotor skills adapt to the environmental changes for survival. Likewise, the ability to morph and acquire new skills can facilitate an embodied agent to solve tasks of varying complexities. In this work, we introduce a data-driven approach where effective hand designs naturally emerge for the purpose of grasping diverse objects. Jointly optimizing morphology and control imposes computational challenges since it requires constant evaluation of a black-box function that measures the performance of a combination of embodiment and behavior. We develop a novel Bayesian Optimization algorithm that efficiently co-designs the morphology and grasping skills jointly through learned latent-space representations. We design the grasping tasks based on a taxonomy of three human grasp types: power grasp, pinch grasp, and lateral grasp. Through experimentation and comparative study, we demonstrate the effectiveness of our approach in discovering robust and cost-efficient hand morphologies for grasping novel objects.
Multi-goal reaching is an important problem in reinforcement learning needed to achieve algorithmic generalization. Despite recent advances in this field, current algorithms suffer from three major challenges: high sample complexity, learning only a single way of reaching the goals, and difficulties in solving complex motion planning tasks. In order to address these limitations, we introduce the concept of cumulative accessibility functions, which measure the reachability of a goal from a given state within a specified horizon. We show that these functions obey a recurrence relation, which enables learning from offline interactions. We also prove that optimal cumulative accessibility functions are monotonic in the planning horizon. Additionally, our method can trade off speed and reliability in goal-reaching by suggesting multiple paths to a single goal depending on the provided horizon. We evaluate our approach on a set of multi-goal discrete and continuous control tasks. We show that our method outperforms state-of-the-art goal-reaching algorithms in success rate, sample complexity, and path optimality. Additional visualizations can be found at https://sites.google.com/view/learning-cae/.
To quickly solve new tasks in complex environments, intelligent agents need to build up reusable knowledge. For example, a learned world model captures knowledge about the environment that applies to new tasks. Similarly, skills capture general behaviors that can apply to new tasks. In this paper, we investigate how these two approaches can be integrated into a single reinforcement learning agent. Specifically, we leverage the idea of partial amortization for fast adaptation at test time. For this, actions are produced by a policy that is learned over time while the skills it conditions on are chosen using online planning. We demonstrate the benefits of our design decisions across a suite of challenging locomotion tasks and demonstrate improved sample efficiency in single tasks as well as in transfer from one task to another, as compared to competitive baselines. Videos are available at: https://sites.google.com/view/partial-amortization-hierarchy/home