arXiv subjects

Andrey Kolobov

Publications and source records attributed to Andrey Kolobov.

33 records · Page 2Linked to original sources

arXiv2023

Survival Instinct in Offline Reinforcement Learning

We present a novel observation about the behavior of offline reinforcement learning (RL) algorithms: on many benchmark datasets, offline RL can produce well-performing and safe policies even when trained with "wrong" reward labels, such as those that are zero everywhere or are negatives of the true rewards. This phenomenon cannot be easily explained by offline RL's return maximization objective. Moreover, it gives offline RL a degree of robustness that is uncharacteristic of its online RL counterparts, which are known to be sensitive to reward design. We demonstrate that this surprising robustness property is attributable to an interplay between the notion of pessimism in offline RL algorithms and certain implicit biases in common data collection practices. As we prove in this work, pessimism endows the agent with a "survival instinct", i.e., an incentive to stay within the data support in the long term, while the limited and biased data coverage further constrains the set of survival policies. Formally, given a reward class -- which may not even contain the true reward -- we identify conditions on the training data distribution that enable offline RL to learn a near-optimal and safe policy from any reward within the class. We argue that the survival instinct should be taken into account when interpreting results from existing offline RL benchmarks and when creating future ones. Our empirical and theoretical results suggest a new paradigm for RL, whereby an agent is nudged to learn a desirable behavior with imperfect reward but purposely biased data coverage.

cs.LG↗

arXiv2023

Interactive Robot Learning from Verbal Correction

The ability to learn and refine behavior after deployment has become ever more important for robots as we design them to operate in unstructured environments like households. In this work, we design a new learning system based on large language model (LLM), OLAF, that allows everyday users to teach a robot using verbal corrections when the robot makes mistakes, e.g., by saying "Stop what you're doing. You should move closer to the cup." A key feature of OLAF is its ability to update the robot's visuomotor neural policy based on the verbal feedback to avoid repeating mistakes in the future. This is in contrast to existing LLM-based robotic systems, which only follow verbal commands or corrections but not learn from them. We demonstrate the efficacy of our design in experiments where a user teaches a robot to perform long-horizon manipulation tasks both in simulation and on physical hardware, achieving on average 20.0% improvement in policy success rate. Videos and more results are at https://ut-austin-rpl.github.io/olaf/

cs.RO↗

arXiv2023

Goal Representations for Instruction Following: A Semi-Supervised Language Interface to Control

Our goal is for robots to follow natural language instructions like "put the towel next to the microwave." But getting large amounts of labeled data, i.e. data that contains demonstrations of tasks labeled with the language instruction, is prohibitive. In contrast, obtaining policies that respond to image goals is much easier, because any autonomous trial or demonstration can be labeled in hindsight with its final state as the goal. In this work, we contribute a method that taps into joint image- and goal- conditioned policies with language using only a small amount of language data. Prior work has made progress on this using vision-language models or by jointly training language-goal-conditioned policies, but so far neither method has scaled effectively to real-world robot tasks without significant human annotation. Our method achieves robust performance in the real world by learning an embedding from the labeled data that aligns language not to the goal image, but rather to the desired change between the start and goal images that the instruction corresponds to. We then train a policy on this embedding: the policy benefits from all the unlabeled data, but the aligned embedding provides an interface for language to steer the policy. We show instruction following across a variety of manipulation tasks in different scenes, with generalization to language instructions outside of the labeled data. Videos and code for our approach can be found on our website: https://rail-berkeley.github.io/grif/ .

cs.RO↗

arXiv2023

MoCapAct: A Multi-Task Dataset for Simulated Humanoid Control

Simulated humanoids are an appealing research domain due to their physical capabilities. Nonetheless, they are also challenging to control, as a policy must drive an unstable, discontinuous, and high-dimensional physical system. One widely studied approach is to utilize motion capture (MoCap) data to teach the humanoid agent low-level skills (e.g., standing, walking, and running) that can then be re-used to synthesize high-level behaviors. However, even with MoCap data, controlling simulated humanoids remains very hard, as MoCap data offers only kinematic information. Finding physical control inputs to realize the demonstrated motions requires computationally intensive methods like reinforcement learning. Thus, despite the publicly available MoCap data, its utility has been limited to institutions with large-scale compute. In this work, we dramatically lower the barrier for productive research on this topic by training and releasing high-quality agents that can track over three hours of MoCap data for a simulated humanoid in the dm_control physics-based environment. We release MoCapAct (Motion Capture with Actions), a dataset of these expert agents and their rollouts, which contain proprioceptive observations and actions. We demonstrate the utility of MoCapAct by using it to train a single hierarchical policy capable of tracking the entire MoCap dataset within dm_control and show the learned low-level component can be re-used to efficiently learn downstream high-level tasks. Finally, we use MoCapAct to train an autoregressive GPT model and show that it can control a simulated humanoid to perform natural motion completion given a motion prompt. Videos of the results and links to the code and dataset are available at https://microsoft.github.io/MoCapAct.

cs.RO↗

arXiv2023

Exploring Levels of Control for a Navigation Assistant for Blind Travelers

Only a small percentage of blind and low-vision people use traditional mobility aids such as a cane or a guide dog. Various assistive technologies have been proposed to address the limitations of traditional mobility aids. These devices often give either the user or the device majority of the control. In this work, we explore how varying levels of control affect the users' sense of agency, trust in the device, confidence, and successful navigation. We present Glide, a novel mobility aid with two modes for control: Glide-directed and User-directed. We employ Glide in a study (N=9) in which blind or low-vision participants used both modes to navigate through an indoor environment. Overall, participants found that Glide was easy to use and learn. Most participants trusted Glide despite its current limitations, and their confidence and performance increased as they continued to use Glide. Users' control mode preference varied in different situations; no single mode "won" in all situations.

cs.RO↗

arXiv2022

Cross-Trajectory Representation Learning for Zero-Shot Generalization in RL

A highly desirable property of a reinforcement learning (RL) agent -- and a major difficulty for deep RL approaches -- is the ability to generalize policies learned on a few tasks over a high-dimensional observation space to similar tasks not seen during training. Many promising approaches to this challenge consider RL as a process of training two functions simultaneously: a complex nonlinear encoder that maps high-dimensional observations to a latent representation space, and a simple linear policy over this space. We posit that a superior encoder for zero-shot generalization in RL can be trained by using solely an auxiliary SSL objective if the training process encourages the encoder to map behaviorally similar observations to similar representations, as reward-based signal can cause overfitting in the encoder (Raileanu et al., 2021). We propose Cross-Trajectory Representation Learning (CTRL), a method that runs within an RL agent and conditions its encoder to recognize behavioral similarity in observations by applying a novel SSL objective to pairs of trajectories from the agent's policies. CTRL can be viewed as having the same effect as inducing a pseudo-bisimulation metric but, crucially, avoids the use of rewards and associated overfitting risks. Our experiments ablate various components of CTRL and demonstrate that in combination with PPO it achieves better generalization performance on the challenging Procgen benchmark suite (Cobbe et al., 2020).

cs.LG↗

arXiv2021

Heuristic-Guided Reinforcement Learning

We provide a framework for accelerating reinforcement learning (RL) algorithms by heuristics constructed from domain knowledge or offline data. Tabula rasa RL algorithms require environment interactions or computation that scales with the horizon of the sequential decision-making task. Using our framework, we show how heuristic-guided RL induces a much shorter-horizon subproblem that provably solves the original task. Our framework can be viewed as a horizon-based regularization for controlling bias and variance in RL under a finite interaction budget. On the theoretical side, we characterize properties of a good heuristic and its impact on RL acceleration. In particular, we introduce the novel concept of an improvable heuristic, a heuristic that allows an RL agent to extrapolate beyond its prior knowledge. On the empirical side, we instantiate our framework to accelerate several state-of-the-art algorithms in simulated robotic control tasks and procedurally generated games. Our framework complements the rich literature on warm-starting RL with expert demonstrations or exploratory datasets, and introduces a principled method for injecting prior knowledge into RL.

cs.LG↗

arXiv2021

Measuring Sample Efficiency and Generalization in Reinforcement Learning Benchmarks: NeurIPS 2020 Procgen Benchmark

The NeurIPS 2020 Procgen Competition was designed as a centralized benchmark with clearly defined tasks for measuring Sample Efficiency and Generalization in Reinforcement Learning. Generalization remains one of the most fundamental challenges in deep reinforcement learning, and yet we do not have enough benchmarks to measure the progress of the community on Generalization in Reinforcement Learning. We present the design of a centralized benchmark for Reinforcement Learning which can help measure Sample Efficiency and Generalization in Reinforcement Learning by doing end to end evaluation of the training and rollout phases of thousands of user submitted code bases in a scalable way. We designed the benchmark on top of the already existing Procgen Benchmark by defining clear tasks and standardizing the end to end evaluation setups. The design aims to maximize the flexibility available for researchers who wish to design future iterations of such benchmarks, and yet imposes necessary practical constraints to allow for a system like this to scale. This paper presents the competition setup and the details and analysis of the top solutions identified through this setup in context of 2020 iteration of the competition at NeurIPS.

cs.LG↗

arXiv2021

Safe Reinforcement Learning via Curriculum Induction

In safety-critical applications, autonomous agents may need to learn in an environment where mistakes can be very costly. In such settings, the agent needs to behave safely not only after but also while learning. To achieve this, existing safe reinforcement learning methods make an agent rely on priors that let it avoid dangerous situations during exploration with high probability, but both the probabilistic guarantees and the smoothness assumptions inherent in the priors are not viable in many scenarios of interest such as autonomous driving. This paper presents an alternative approach inspired by human teaching, where an agent learns under the supervision of an automatic instructor that saves the agent from violating constraints during learning. In this model, we introduce the monitor that neither needs to know how to do well at the task the agent is learning nor needs to know how the environment works. Instead, it has a library of reset controllers that it activates when the agent starts behaving dangerously, preventing it from doing damage. Crucially, the choices of which reset controller to apply in which situation affect the speed of agent learning. Based on observing agents' progress, the teacher itself learns a policy for choosing the reset controllers, a curriculum, to optimize the agent's final policy reward. Our experiments use this framework in two environments to induce curricula for safe and efficient learning.

cs.LG↗

arXiv2020

Policy Improvement via Imitation of Multiple Oracles

Despite its promise, reinforcement learning's real-world adoption has been hampered by the need for costly exploration to learn a good policy. Imitation learning (IL) mitigates this shortcoming by using an oracle policy during training as a bootstrap to accelerate the learning process. However, in many practical situations, the learner has access to multiple suboptimal oracles, which may provide conflicting advice in a state. The existing IL literature provides a limited treatment of such scenarios. Whereas in the single-oracle case, the return of the oracle's policy provides an obvious benchmark for the learner to compete against, neither such a benchmark nor principled ways of outperforming it are known for the multi-oracle setting. In this paper, we propose the state-wise maximum of the oracle policies' values as a natural baseline to resolve conflicting advice from multiple oracles. Using a reduction of policy optimization to online learning, we introduce a novel IL algorithm MAMBA, which can provably learn a policy competitive with this benchmark. In particular, MAMBA optimizes policies by using a gradient estimator in the style of generalized advantage estimation (GAE). Our theoretical analysis shows that this design makes MAMBA robust and enables it to outperform the oracle policies by a larger margin than the IL state of the art, even in the single-oracle case. In an evaluation against standard policy gradient with GAE and AggreVaTe(D), we showcase MAMBA's ability to leverage demonstrations both from a single and from multiple weak oracles, and significantly speed up policy optimization.

cs.LG↗

arXiv2020

Online Learning for Active Cache Synchronization

Existing multi-armed bandit (MAB) models make two implicit assumptions: an arm generates a payoff only when it is played, and the agent observes every payoff that is generated. This paper introduces synchronization bandits, a MAB variant where all arms generate costs at all times, but the agent observes an arm's instantaneous cost only when the arm is played. Synchronization MABs are inspired by online caching scenarios such as Web crawling, where an arm corresponds to a cached item and playing the arm means downloading its fresh copy from a server. We present MirrorSync, an online learning algorithm for synchronization bandits, establish an adversarial regret of $O(T^{2/3})$ for it, and show how to make it practical.

cs.LG↗

arXiv2018

ArduSoar: an Open-Source Thermalling Controller for Resource-Constrained Autopilots

Autonomous soaring capability has the potential to significantly increase time aloft for fixed-wing UAVs. In this paper, we introduce ArduSoar, the first soaring controller integrated into a major autopilot software suite for small UAVs. We describe ArduSoar from the algorithmic standpoint, outline its integration with the ArduPlane autopilot, discuss parameter tuning for it, and conduct a series of flight tests on real sUAVs that show ArduSoar's robustness even in highly non-ideal atmospheric conditions.

cs.RO↗

arXiv2018

Autonomous Thermalling as a Partially Observable Markov Decision Process (Extended Version)

Small uninhabited aerial vehicles (sUAVs) commonly rely on active propulsion to stay airborne, which limits flight time and range. To address this, autonomous soaring seeks to utilize free atmospheric energy in the form of updrafts (thermals). However, their irregular nature at low altitudes makes them hard to exploit for existing methods. We model autonomous thermalling as a POMDP and present a receding-horizon controller based on it. We implement it as part of ArduPlane, a popular open-source autopilot, and compare it to an existing alternative in a series of live flight tests involving two sUAVs thermalling simultaneously, with our POMDP-based controller showing a significant advantage.

cs.RO↗

arXiv2015

Metareasoning for Planning Under Uncertainty

The conventional model for online planning under uncertainty assumes that an agent can stop and plan without incurring costs for the time spent planning. However, planning time is not free in most real-world settings. For example, an autonomous drone is subject to nature's forces, like gravity, even while it thinks, and must either pay a price for counteracting these forces to stay in place, or grapple with the state change caused by acquiescing to them. Policy optimization in these settings requires metareasoning---a process that trades off the cost of planning and the potential policy improvement that can be achieved. We formalize and analyze the metareasoning problem for Markov Decision Processes (MDPs). Our work subsumes previously studied special cases of metareasoning and shows that in the general case, metareasoning is at most polynomially harder than solving MDPs with any given algorithm that disregards the cost of thinking. For reasons we discuss, optimal general metareasoning turns out to be impractical, motivating approximations. We present approximate metareasoning procedures which rely on special properties of the BRTDP planning algorithm and explore the effectiveness of our methods on a variety of problems.

cs.AI↗

arXiv2012

A Theory of Goal-Oriented MDPs with Dead Ends

Stochastic Shortest Path (SSP) MDPs is a problem class widely studied in AI, especially in probabilistic planning. They describe a wide range of scenarios but make the restrictive assumption that the goal is reachable from any state, i.e., that dead-end states do not exist. Because of this, SSPs are unable to model various scenarios that may have catastrophic events (e.g., an airplane possibly crashing if it flies into a storm). Even though MDP algorithms have been used for solving problems with dead ends, a principled theory of SSP extensions that would allow dead ends, including theoretically sound algorithms for solving such MDPs, has been lacking. In this paper, we propose three new MDP classes that admit dead ends under increasingly weaker assumptions. We present Value Iteration-based as well as the more efficient heuristic search algorithms for optimally solving each class, and explore theoretical relationships between these classes. We also conduct a preliminary empirical study comparing the performance of our algorithms on different MDP classes, especially on scenarios with unavoidable dead ends.

cs.AI↗