Learning predictive models from interaction with the world allows an agent, such as a robot, to learn about how the world works, and then use this learned model to plan coordinated sequences of actions to bring about desired outcomes. However, learning a model that captures the dynamics of complex skills represents a major challenge: if the agent needs a good model to perform these skills, it might never be able to collect the experience on its own that is required to learn these delicate and complex behaviors. Instead, we can imagine augmenting the training set with observational data of other agents, such as humans. Such data is likely more plentiful, but represents a different embodiment. For example, videos of humans might show a robot how to use a tool, but (i) are not annotated with suitable robot actions, and (ii) contain a systematic distributional shift due to the embodiment differences between humans and robots. We address the first challenge by formulating the corresponding graphical model and treating the action as an observed variable for the interaction data and an unobserved variable for the observation data, and the second challenge by using a domain-dependent prior. In addition to interaction data, our method is able to leverage videos of passive observations in a driving dataset and a dataset of robotic manipulation videos. A robotic planning agent equipped with our method can learn to use tools in a tabletop robotic manipulation setting by observing humans without ever seeing a robotic video of tool use.
The ability to learn new concepts with small amounts of data is a critical aspect of intelligence that has proven challenging for deep learning methods. Meta-learning has emerged as a promising technique for leveraging data from previous tasks to enable efficient learning of new tasks. However, most meta-learning algorithms implicitly require that the meta-training tasks be mutually-exclusive, such that no single model can solve all of the tasks at once. For example, when creating tasks for few-shot image classification, prior work uses a per-task random assignment of image classes to N-way classification labels. If this is not done, the meta-learner can ignore the task training data and learn a single model that performs all of the meta-training tasks zero-shot, but does not adapt effectively to new image classes. This requirement means that the user must take great care in designing the tasks, for example by shuffling labels or removing task identifying information from the inputs. In some domains, this makes meta-learning entirely inapplicable. In this paper, we address this challenge by designing a meta-regularization objective using information theory that places precedence on data-driven adaptation. This causes the meta-learner to decide what must be learned from the task training data and what should be inferred from the task testing input. By doing so, our algorithm can successfully use data from non-mutually-exclusive tasks to efficiently adapt to novel tasks. We demonstrate its applicability to both contextual and gradient-based meta-learning algorithms, and apply it in practical settings where applying standard meta-learning has been difficult. Our approach substantially outperforms standard meta-learning algorithms in these settings.
Imitation learning algorithms provide a simple and straightforward approach for training control policies via supervised learning. By maximizing the likelihood of good actions provided by an expert demonstrator, supervised imitation learning can produce effective policies without the algorithmic complexities and optimization challenges of reinforcement learning, at the cost of requiring an expert demonstrator to provide the demonstrations. In this paper, we ask: can we take insights from imitation learning to design algorithms that can effectively acquire optimal policies from scratch without any expert demonstrations? The key observation that makes this possible is that, in the multi-task setting, trajectories that are generated by a suboptimal policy can still serve as optimal examples for other tasks. In particular, when tasks correspond to different goals, every trajectory is a successful demonstration for the goal state that it actually reaches. We propose a simple algorithm for learning goal-reaching behaviors without any demonstrations, complicated user-provided reward functions, or complex reinforcement learning methods. Our method simply maximizes the likelihood of actions the agent actually took in its own previous rollouts, conditioned on the goal being the state that it actually reached. Although related variants of this approach have been proposed previously in imitation learning with demonstrations, we show how this approach can effectively learn goal-reaching policies from scratch. We present a theoretical result linking self-supervised imitation learning and reinforcement learning, and empirical results showing that it performs competitively with more complex reinforcement learning methods on a range of challenging goal reaching problems, while yielding advantages in terms of stability and use of offline data.
All living organisms struggle against the forces of nature to carve out niches where they can maintain homeostasis. We propose that such a search for order amidst chaos might offer a unifying principle for the emergence of useful behaviors in artificial agents. We formalize this idea into an unsupervised reinforcement learning method called surprise minimizing RL (SMiRL). SMiRL trains an agent with the objective of maximizing the probability of observed states under a model trained on previously seen states. The resulting agents can acquire proactive behaviors that seek out and maintain stable conditions, such as balancing and damage avoidance, that are closely tied to an environment's prevailing sources of entropy, such as wind, earthquakes, and other agents. We demonstrate that our surprise minimizing agents can successfully play Tetris, Doom, control a humanoid to avoid falls and navigate to escape enemy agents, without any task-specific reward supervision. We further show that SMiRL can be used together with a standard task reward to accelerate reward-driven learning.
Robotic reinforcement learning (RL) holds the promise of enabling robots to learn complex behaviors through experience. However, realizing this promise requires not only effective and scalable RL algorithms, but also mechanisms to reduce human burden in terms of defining the task and resetting the environment. In this paper, we study how these challenges can be alleviated with an automated robotic learning framework, in which multi-stage tasks are defined simply by providing videos of a human demonstrator and then learned autonomously by the robot from raw image observations. A central challenge in imitating human videos is the difference in morphology between the human and robot, which typically requires manual correspondence. We instead take an automated approach and perform pixel-level image translation via CycleGAN to convert the human demonstration into a video of a robot, which can then be used to construct a reward function for a model-based RL algorithm. The robot then learns the task one stage at a time, automatically learning how to reset each stage to retry it multiple times without human-provided resets. This makes the learning process largely automatic, from intuitive task specification via a video to automated training with minimal human intervention. We demonstrate that our approach is capable of learning complex tasks, such as operating a coffee machine, directly from raw image observations, requiring only 20 minutes to provide human demonstrations and about 180 minutes of robot interaction with the environment. A supplementary video depicting the experimental setup, learning process, and our method's final performance is available from https://sites.google.com/view/icra20avid
In principle, meta-reinforcement learning algorithms leverage experience across many tasks to learn fast reinforcement learning (RL) strategies that transfer to similar tasks. However, current meta-RL approaches rely on manually-defined distributions of training tasks, and hand-crafting these task distributions can be challenging and time-consuming. Can "useful" pre-training tasks be discovered in an unsupervised manner? We develop an unsupervised algorithm for inducing an adaptive meta-training task distribution, i.e. an automatic curriculum, by modeling unsupervised interaction in a visual environment. The task distribution is scaffolded by a parametric density model of the meta-learner's trajectory distribution. We formulate unsupervised meta-RL as information maximization between a latent task variable and the meta-learner's data distribution, and describe a practical instantiation which alternates between integration of recent experience into the task distribution and meta-learning of the updated tasks. Repeating this procedure leads to iterative reorganization such that the curriculum adapts as the meta-learner's data distribution shifts. In particular, we show how discriminative clustering for visual representation can support trajectory-level task acquisition and exploration in domains with pixel observations, avoiding pitfalls of alternatives. In experiments on vision-based navigation and manipulation domains, we show that the algorithm allows for unsupervised meta-learning that transfers to downstream tasks specified by hand-crafted reward functions and serves as pre-training for more efficient supervised meta-learning of test task distributions.
We seek to align agent behavior with a user's objectives in a reinforcement learning setting with unknown dynamics, an unknown reward function, and unknown unsafe states. The user knows the rewards and unsafe states, but querying the user is expensive. To address this challenge, we propose an algorithm that safely and interactively learns a model of the user's reward function. We start with a generative model of initial states and a forward dynamics model trained on off-policy data. Our method uses these models to synthesize hypothetical behaviors, asks the user to label the behaviors with rewards, and trains a neural network to predict the rewards. The key idea is to actively synthesize the hypothetical behaviors from scratch by maximizing tractable proxies for the value of information, without interacting with the environment. We call this method reward query synthesis via trajectory optimization (ReQueST). We evaluate ReQueST with simulated users on a state-based 2D navigation task and the image-based Car Racing video game. The results show that ReQueST significantly outperforms prior methods in learning reward models that transfer to new environments with different initial state distributions. Moreover, ReQueST safely trains the reward model to detect unsafe states, and corrects reward hacking before deploying the agent.
This paper tests the hypothesis that modeling a scene in terms of entities and their local interactions, as opposed to modeling the scene globally, provides a significant benefit in generalizing to physical tasks in a combinatorial space the learner has not encountered before. We present object-centric perception, prediction, and planning (OP3), which to the best of our knowledge is the first entity-centric dynamic latent variable framework for model-based reinforcement learning that acquires entity representations from raw visual observations without supervision and uses them to predict and plan. OP3 enforces entity-abstraction -- symmetric processing of each entity representation with the same locally-scoped function -- which enables it to scale to model different numbers and configurations of objects from those in training. Our approach to solving the key technical challenge of grounding these entity representations to actual objects in the environment is to frame this variable binding problem as an inference problem, and we developing an interactive inference algorithm that uses temporal continuity and interactive feedback to bind information about object properties to the entity variables. On block-stacking tasks, OP3 generalizes to novel block configurations and more objects than observed during training, outperforming an oracle model that assumes access to object supervision and achieving two to three times better accuracy than a state-of-the-art video prediction model.