Title: Effectively Learning Initiation Sets in Hierarchical Reinforcement Learning
An agent learning an option in hierarchical reinforcement learning must solve three problems: identify the option’s subgoal (termination condition), learn a policy, and learn where that policy will succeed (initiation set). The termination condition is typically identified first, but the option policy and initiation set must be learned simultaneously, which is challenging because the initiation set depends on the option policy, which changes as the agent learns. Consequently, data obtained from option execution becomes invalid over time, leading to an inaccurate initiation set that subsequently harms downstream task performance. We highlight three issues—data non-stationarity, temporal credit assignment, and pessimism—specific to learning initiation sets, and propose to address them using tools from off-policy value estimation and classification. We show that our method learns higher-quality initiation sets faster than existing methods (in MINIGRID and MONTEZUMA’S REVENGE), can automatically discover promising grasps for robot manipulation (in ROBOSUITE), and improves the performance of a state-of-the-art option discovery method in a challenging maze navigation task in MuJoCo. more »« less
Kunda, Maithilee
(, Proceedings of the Seventh Annual Conference on Advances in Cognitive Systems)
null
(Ed.)
Nonverbal task learning is defined here as a variant of interactive task learning in which an agent learns the definition of a new task without any verbal information such as task instructions. Instead, the agent must 1) learn the task definition using only a single solved example problem as its training input, and then 2) generalize this definition in order to successfully parse new problems. In this paper, we present a conceptual framework for nonverbal task learning, and we compare and contrast this type of learning with existing learning paradigms in AI. We also discuss nonverbal task learning in the context of nonverbal human intelligence tests, which are standardized tests designed to be given without any verbal instructions so that they can be used by people with language difficulties.
Abbatematteo, B; Rosen, E; Tellex, S; Konidaris, G.D.
(, Proceedings of the 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems)
Learning a robot motor skill from scratch is impractically slow; so much so that in practice, learning must typically be bootstrapped using human demonstration. However, relying on human demonstration necessarily degrades the autonomy of robots that must learn a wide variety of skills over their operational lifetimes. We propose using kinematic motion planning as a completely autonomous, sample efficient way to bootstrap motor skill learning for object manipulation. We demonstrate the use of motion planners to bootstrap motor skills in two complex object manipulation scenarios with different policy representations: opening a drawer with a dynamic movement primitive representation, and closing a microwave door with a deep neural network policy. We also show how our method can bootstrap a motor skill for the challenging dynamic task of learning to hit a ball off a tee, where a kinematic plan based on treating the scene as static is insufficient to solve the task, but sufficient to bootstrap a more dynamic policy. In all three cases, our method is competitive with human-demonstrated initialization, and significantly outperforms starting with a random policy. This approach enables robots to to efficiently and autonomously learn motor policies for dynamic tasks without human demonstration.
Neary, Cyrus; Verginis, Christos; Cubuktepe, Murat; Topcu, Ufuk
(, Proceedings of the International Conference on Automated Planning and Scheduling)
We propose a framework for verifiable and compositional reinforcement learning (RL) in which a collection of RL subsystems, each of which learns to accomplish a separate subtask, are composed to achieve an overall task. The framework consists of a high-level model, represented as a parametric Markov decision process (pMDP) which is used to plan and to analyze compositions of subsystems, and of the collection of low-level subsystems themselves. By defining interfaces between the subsystems, the framework enables automatic decompositions of task specifications, e.g., reach a target set of states with a probability of at least 0.95, into individual subtask specifications, i.e. achieve the subsystem's exit conditions with at least some minimum probability, given that its entry conditions are met. This in turn allows for the independent training and testing of the subsystems; if they each learn a policy satisfying the appropriate subtask specification, then their composition is guaranteed to satisfy the overall task specification. Conversely, if the subtask specifications cannot all be satisfied by the learned policies, we present a method, formulated as the problem of finding an optimal set of parameters in the pMDP, to automatically update the subtask specifications to account for the observed shortcomings. The result is an iterative procedure for defining subtask specifications, and for training the subsystems to meet them. As an additional benefit, this procedure allows for particularly challenging or important components of an overall task to be identified automatically, and focused on, during training. Experimental results demonstrate the presented framework's novel capabilities in both discrete and continuous RL settings. A collection of RL subsystems are trained, using proximal policy optimization algorithms, to navigate different portions of a labyrinth environment. A cross-labyrinth task specification is then decomposed into subtask specifications. Challenging portions of the labyrinth are automatically avoided if their corresponding subsystems cannot learn satisfactory policies within allowed training budgets. Unnecessary subsystems are not trained at all. The result is a compositional RL system that efficiently learns to satisfy task specifications.
Krishna, Ranjay; Lee, Donsuk; Fei-Fei, Li; Bernstein, Michael S.
(, Proceedings of the National Academy of Sciences)
Regardless of how much data artificial intelligence agents have available, agents will inevitably encounter previously unseen situations in real-world deployments. Reacting to novel situations by acquiring new information from other people—socially situated learning—is a core faculty of human development. Unfortunately, socially situated learning remains an open challenge for artificial intelligence agents because they must learn how to interact with people to seek out the information that they lack. In this article, we formalize the task of socially situated artificial intelligence—agents that seek out new information through social interactions with people—as a reinforcement learning problem where the agent learns to identify meaningful and informative questions via rewards observed through social interaction. We manifest our framework as an interactive agent that learns how to ask natural language questions about photos as it broadens its visual intelligence on a large photo-sharing social network. Unlike active-learning methods, which implicitly assume that humans are oracles willing to answer any question, our agent adapts its behavior based on observed norms of which questions people are or are not interested to answer. Through an 8-mo deployment where our agent interacted with 236,000 social media users, our agent improved its performance at recognizing new visual information by 112%. A controlled field experiment confirmed that our agent outperformed an active-learning baseline by 25.6%. This work advances opportunities for continuously improving artificial intelligence (AI) agents that better respect norms in open social environments.
Nguyen, Hai Huu; Baisero, Andrea; Wang, Dian; Amato, Christopher; Platt, Robert
(, Conference on Robot Learning)
Reinforcement learning in partially observable domains is challenging due to the lack of observable state information. Thankfully, learning offline in a simulator with such state information is often possible. In particular, we propose a method for partially observable reinforcement learning that uses a fully observable policy (which we call a \emph{state expert}) during training to improve performance. Based on Soft Actor-Critic (SAC), our agent balances performing actions similar to the state expert and getting high returns under partial observability. Our approach can leverage the fully-observable policy for exploration and parts of the domain that are fully observable while still being able to learn under partial observability. On six robotics domains, our method outperforms pure imitation, pure reinforcement learning, the sequential or parallel combination of both types, and a recent state-of-the-art method in the same setting. A successful policy transfer to a physical robot in a manipulation task from pixels shows our approach's practicality in learning interesting policies under partial observability.
Bagaria, Akhil, Abbatematteo, Ben, Gottesman, Omer, Corsaro, Matt, Rammohan, Sreehari, and Konidaris, George.
"Effectively Learning Initiation Sets in Hierarchical Reinforcement Learning". 37th Conference on Neural Information Processing Systems (). Country unknown/Code not available: 37th Conference on Neural Information Processing Systems. https://par.nsf.gov/biblio/10497999.
@article{osti_10497999,
place = {Country unknown/Code not available},
title = {Effectively Learning Initiation Sets in Hierarchical Reinforcement Learning},
url = {https://par.nsf.gov/biblio/10497999},
abstractNote = {An agent learning an option in hierarchical reinforcement learning must solve three problems: identify the option’s subgoal (termination condition), learn a policy, and learn where that policy will succeed (initiation set). The termination condition is typically identified first, but the option policy and initiation set must be learned simultaneously, which is challenging because the initiation set depends on the option policy, which changes as the agent learns. Consequently, data obtained from option execution becomes invalid over time, leading to an inaccurate initiation set that subsequently harms downstream task performance. We highlight three issues—data non-stationarity, temporal credit assignment, and pessimism—specific to learning initiation sets, and propose to address them using tools from off-policy value estimation and classification. We show that our method learns higher-quality initiation sets faster than existing methods (in MINIGRID and MONTEZUMA’S REVENGE), can automatically discover promising grasps for robot manipulation (in ROBOSUITE), and improves the performance of a state-of-the-art option discovery method in a challenging maze navigation task in MuJoCo.},
journal = {37th Conference on Neural Information Processing Systems},
publisher = {37th Conference on Neural Information Processing Systems},
author = {Bagaria, Akhil and Abbatematteo, Ben and Gottesman, Omer and Corsaro, Matt and Rammohan, Sreehari and Konidaris, George},
}
Warning: Leaving National Science Foundation Website
You are now leaving the National Science Foundation website to go to a non-government website.
Website:
NSF takes no responsibility for and exercises no control over the views expressed or the accuracy of
the information contained on this site. Also be aware that NSF's privacy policy does not apply to this site.
An official website of the United States government
