We show that offline actor-critic reinforcement learning can scale to large models - such as transformers - and follows similar scaling laws as supervised learning. We find that offline actor-critic algorithms can outperform strong, supervised, behavioral cloning baselines for multi-task training on a large dataset containing both sub-optimal and expert behavior on 132 continuous control tasks. We introduce a Perceiver-based actor-critic model and elucidate the key model features needed to make offline RL work with self- and cross-attention modules. Overall, we find that: i) simple offline actor critic algorithms are a natural choice for gradually moving away from the currently predominant paradigm of behavioral cloning, and ii) via offline RL it is possible to learn multi-task policies that master many domains simultaneously, including real robotics tasks, from sub-optimal demonstrations or self-generated data.

The ability to leverage heterogeneous robotic experience from different robots and tasks to quickly master novel skills and embodiments has the potential to transform robot learning. Inspired by recent advances in foundation models for vision and language, we propose a multi-embodiment, multi-task generalist agent for robotic manipulation. This agent, named RoboCat, is a visual goal-conditioned decision transformer capable of consuming action-labelled visual experience. This data spans a large repertoire of motor control skills from simulated and real robotic arms with varying sets of observations and actions. With RoboCat, we demonstrate the ability to generalise to new tasks and robots, both zero-shot as well as through adaptation using only 100-1000 examples for the target task. We also show how a trained model itself can be used to generate data for subsequent training iterations, thus providing a basic building block for an autonomous improvement loop. We investigate the agent's capabilities, with large-scale evaluations both in simulation and on three different real robot embodiments. We find that as we grow and diversify its training data, RoboCat not only shows signs of cross-task transfer, but also becomes more efficient at adapting to new tasks.

Reinforcement learning solely from an agent's self-generated data is often believed to be infeasible for learning on real robots, due to the amount of data needed. However, if done right, agents learning from real data can be surprisingly efficient through re-using previously collected sub-optimal data. In this paper we demonstrate how the increased understanding of off-policy learning methods and their embedding in an iterative online/offline scheme (``collect and infer'') can drastically improve data-efficiency by using all the collected experience, which empowers learning from real robot experience only. Moreover, the resulting policy improves significantly over the state of the art on a recently proposed real robot manipulation benchmark. Our approach learns end-to-end, directly from pixels, and does not rely on additional human domain knowledge such as a simulator or demonstrations.

We introduce Robust Exploration via Clusteringbased Online Density Estimation (RECODE), a nonparametric method for novelty-based exploration that estimates visitation counts for clusters of states based on their similarity in a chosen embedding space. By adapting classical clustering to the nonstationary setting of Deep RL, RECODE can efficiently track state visitation counts over thousands of episodes. We further propose a novel generalization of the inverse dynamics loss, which leverages masked transformer architectures for multi-step prediction; which in conjunction with RECODE achieves a new state-of-the-art in Figure 1: A key result of RECODE is that it allows us to a suite of challenging 3D-exploration tasks in leverage more powerful state representations for long-term DM-HARD-8. RECODE also sets new state-of-theart novelty estimation; enabling to achieve a new state-of-theart in hard exploration Atari games, and is the first in the challenging 3D task suite DM-HARD-8.

A BSTRACT In this paper we investigate an artificial agent's ability to perform task-focused tool synthesis via imagination. Our motivation is to explore the richness of information captured by the latent space of an object-centric generative model - and how to exploit it. In particular, our approach employs activation maximisation of a task-based performance predictor to optimise the latent variable of a structured latent-space model in order to generate tool geometries appropriate for the task at hand. We evaluate our model using a novel dataset of synthetic reaching tasks inspired by the cognitive sciences and behavioural ecology. In doing so we examine the model's ability to imagine tools for increasingly complex scenario types, beyond those seen during training. Our experiments demonstrate that the synthesis process modifies emergent, task-relevant object affordances in a targeted and deliberate way: the agents often specifically modify aspects of the tools which relate to meaningful (yet implicitly learned) concepts such as a tool's length, width and configuration. Our results therefore suggest that task relevant object affordances are implicitly encoded as directions in a structured latent space shaped by experience. 1 I NTRODUCTION Deep generative models are gaining in popularity for unsupervised representation learning. In particular, recent models like MONet (Burgess et al., 2019) have been proposed to decompose scenes into object-centric latent representations (cf. The notion of such an object-centric latent representation, trained from examples in an unsupervised way, holds a tantalising prospect: as generative models naturally capture factors of variation, could they also be used to expose these factors such that they can be modified in a task-driven way? We posit that a task-driven traversal of a structured latent space leads to affordances emerging naturally as directions in this space. This is in stark contrast to more common approaches to affordance learning where it is commonly achieved via direct supervision or implicitly via imitation (e.g. Tikhanoff et al., 2013; Myers et al., 2015; Liu et al., 2018; Grabner et al., 2011; Do et al., 2018).

Model interpretability and systematic, targeted model adaptation present central tenets in machine learning for addressing limited or biased datasets. In this paper, we introduce neural stethoscopes as a framework for quantifying the degree of importance of specific factors of influence in deep networks as well as for actively promoting and suppressing information as appropriate. In doing so we unify concepts from multitask learning as well as training with auxiliary and adversarial losses. We showcase the efficacy of neural stethoscopes in an intuitive physics domain. Specifically, we investigate the challenge of visually predicting stability of block towers and demonstrate that the network uses visual cues which makes it susceptible to biases in the dataset. Through the use of stethoscopes we interrogate the accessibility of specific information throughout the network stack and show that we are able to actively de-bias network predictions as well as enhance performance via suitable auxiliary and adversarial stethoscope losses.