Learning Time-Invariant Reward Functions through Model-Based Inverse Reinforcement Learning

Inverse reinforcement learning is a paradigm motivated by the goal of learning general reward functions from demonstrated behaviours. Yet the notion of generality for learnt costs is often evaluated in terms of robustness to various spatial perturbations only, assuming deployment at fixed speeds of execution. However, this is impractical in the context of robotics and building time-invariant solutions is of crucial importance. In this work, we propose a formulation that allows us to 1) vary the length of execution by learning time-invariant costs, and 2) relax the temporal alignment requirements for learning from demonstration. We apply our method to two different types of cost formulations and evaluate their performance in the context of learning reward functions for simulated placement and peg in hole tasks. Our results show that our approach enables learning temporally invariant rewards from misaligned demonstration that can also generalise spatially to out of distribution tasks.

Habitat 2.0: Training Home Assistants to Rearrange their Habitat

We introduce Habitat 2.0 (H2.0), a simulation platform for training virtual robots in interactive 3D environments and complex physics-enabled scenarios. We make comprehensive contributions to all levels of the embodied AI stack - data, simulation, and benchmark tasks. Specifically, we present: (i) ReplicaCAD: an artist-authored, annotated, reconfigurable 3D dataset of apartments (matching real spaces) with articulated objects (e.g. cabinets and drawers that can open/close); (ii) H2.0: a high-performance physics-enabled 3D simulator with speeds exceeding 25,000 simulation steps per second (850x real-time) on an 8-GPU node, representing 100x speed-ups over prior work; and, (iii) Home Assistant Benchmark (HAB): a suite of common tasks for assistive robots (tidy the house, prepare groceries, set the table) that test a range of mobile manipulation capabilities. These large-scale engineering contributions allow us to systematically compare deep reinforcement learning (RL) at scale and classical sense-plan-act (SPA) pipelines in long-horizon structured tasks, with an emphasis on generalization to new objects, receptacles, and layouts. We find that (1) flat RL policies struggle on HAB compared to hierarchical ones; (2) a hierarchy with independent skills suffers from 'hand-off problems', and (3) SPA pipelines are more brittle than RL policies.

Learning Navigation Skills for Legged Robots with Learned Robot Embeddings

Navigation policies are commonly learned on idealized cylinder agents in simulation, without modelling complex dynamics, like contact dynamics, arising from the interaction between the robot and the environment. Such policies perform poorly when deployed on complex and dynamic robots, such as legged robots. In this work, we learn hierarchical navigation policies that account for the low-level dynamics of legged robots, such as maximum speed, slipping, and achieve good performance at navigating cluttered indoor environments. Once such a policy is learned on one legged robot, it does not directly generalize to a different robot due to dynamical differences, which increases the cost of learning such a policy on new robots. To overcome this challenge, we learn dynamics-aware navigation policies across multiple robots with robot-specific embeddings, which enable generalization to new unseen robots. We train our policies across three legged robots - 2 quadrupeds (A1, AlienGo) and a hexapod (Daisy). At test time, we study the performance of our learned policy on two new legged robots (Laikago, 4-legged Daisy) and show that our learned policy can sample-efficiently generalize to previously unseen robots.

Learning Extended Body Schemas from Visual Keypoints for Object Manipulation

Humans have impressive generalization capabilities when it comes to manipulating objects and tools in completely novel environments. These capabilities are, at least partially, a result of humans having internal models of their bodies and any grasped object. How to learn such body schemas for robots remains an open problem. In this work, we develop an approach that can extend a robot's kinematic model when grasping an object from visual latent representations. Our framework comprises two components: 1) a structured keypoint detector, which fuses proprioception and vision to predict visual key points on an object; 2) Learning an adaptation of the kinematic chain by regressing virtual joints from the predicted key points. Our evaluation shows that our approach learns to consistently predict visual keypoints on objects, and can easily adapt a kinematic chain to the object grasped in various configurations, from a few seconds of data. Finally we show that this extended kinematic chain lends itself for object manipulation tasks such as placing a grasped object.

Leveraging Forward Model Prediction Error for Learning Control

Learning for model based control can be sample-efficient and generalize well, however successfully learning models and controllers that represent the problem at hand can be challenging for complex tasks. Using inaccurate models for learning can lead to sub-optimal solutions, that are unlikely to perform well in practice. In this work, we present a learning approach which iterates between model learning and data collection and leverages forward model prediction error for learning control. We show how using the controller's prediction as input to a forward model can create a differentiable connection between the controller and the model, allowing us to formulate a loss in the state space. This lets us include forward model prediction error during controller learning and we show that this creates a loss objective that significantly improves learning on different motor control tasks. We provide empirical and theoretical results that show the benefits of our method and present evaluations in simulation for learning control on a 7 DoF manipulator and an underactuated 12 DoF quadruped. We show that our approach successfully learns controllers for challenging motor control tasks involving contact switching.

Exploring Zero-Shot Emergent Communication in Embodied Multi-Agent Populations

Effective communication is an important skill for enabling information exchange and cooperation in multi-agent settings. Indeed, emergent communication is now a vibrant field of research, with common settings involving discrete cheap-talk channels. One limitation of this setting is that it does not allow for the emergent protocols to generalize beyond the training partners. Furthermore, so far emergent communication has primarily focused on the use of symbolic channels. In this work, we extend this line of work to a new modality, by studying agents that learn to communicate via actuating their joints in a 3D environment. We show that under realistic assumptions, a non-uniform distribution of intents and a common-knowledge energy cost, these agents can find protocols that generalize to novel partners. We also explore and analyze specific difficulties associated with finding these solutions in practice. Finally, we propose and evaluate initial training improvements to address these challenges, involving both specific training curricula and providing the latent feature that can be coordinated on during training.

Model-Based Inverse Reinforcement Learning from Visual Demonstrations

Scaling model-based inverse reinforcement learning (IRL) to real robotic manipulation tasks with unknown dynamics remains an open problem. The key challenges lie in learning good dynamics models, developing algorithms that scale to high-dimensional state-spaces and being able to learn from both visual and proprioceptive demonstrations. In this work, we present a gradient-based inverse reinforcement learning framework that utilizes a pre-trained visual dynamics model to learn cost functions when given only visual human demonstrations. The learned cost functions are then used to reproduce the demonstrated behavior via visual model predictive control. We evaluate our framework on hardware on two basic object manipulation tasks.

Planning in Learned Latent Action Spaces for Generalizable Legged Locomotion

Hierarchical learning has been successful at learning generalizable locomotion skills on walking robots in a sample-efficient manner. However, the low-dimensional "latent" action used to communicate between different layers of the hierarchy is typically user-designed. In this work, we present a fully-learned hierarchical framework, that is capable of jointly learning the low-level controller and the high-level action space. Next, we plan over latent actions in a model-predictive control fashion, using a learned high-level dynamics model. This framework is generalizable to multiple robots, and we present results on a Daisy hexapod simulation, A1 quadruped simulation, and Daisy robot hardware. We compare a range of learned hierarchical approaches, and show that our framework is more reliable, versatile and sample-efficient. In addition to learning approaches, we also compare to an inverse-kinematics (IK) based footstep planner, and show that our fully-learned framework is competitive in performance with IK under normal conditions, and outperforms it in adverse settings. Our hardware experiments show the Daisy hexapod achieving multiple locomotion tasks, such as goal reaching, trajectory and velocity tracking in an unstructured outdoor setting, with only 2000 hardware samples.

Residual Learning from Demonstration

Contacts and friction are inherent to nearly all robotic manipulation tasks. Through the motor skill of insertion, we study how robots can learn to cope when these attributes play a salient role. In this work we propose residual learning from demonstration (rLfD), a framework that combines dynamic movement primitives (DMP) that rely on behavioural cloning with a reinforcement learning (RL) based residual correction policy. The proposed solution is applied directly in task space and operates on the full pose of the robot. We show that rLfD outperforms alternatives and improves the generalisation abilities of DMPs. We evaluate this approach by training an agent to successfully perform both simulated and real world insertions of pegs, gears and plugs into respective sockets.