An official website of the United States government
We develop a framework to learn bio-inspired foraging policies using human data. We conduct an experiment where humans are virtually immersed in an open field foraging environment and are trained to collect the highest amount of rewards. A Markov Decision Process (MDP) framework is introduced to model the human decision dynamics. Then, Imitation Learning (IL) based on maximum likelihood estimation is used to train Neural Networks (NN) that map human decisions to observed states. The results show that passive imitation substantially underperforms humans. We further refine the human-inspired policies via Reinforcement Learning (RL) using the on-policy Proximal Policy Optimization (PPO) algorithm which shows better stability than other algorithms and can steadily improve the policies pre-trained with IL. We show that the combination of IL and RL match human performance and that the artificial agents trained with our approach can quickly adapt to reward distribution shift. We finally show that good performance and robustness to reward distribution shift strongly depend on combining allocentric information with an egocentric representation of the environment.
more »
« less
Model reusability in Reinforcement Learning
Abstract The ability to reuse trained models in Reinforcement Learning (RL) holds substantial practical value in particular for complex tasks. While model reusability is widely studied for supervised models in data management, to the best of our knowledge, this is the first ever principled study that is proposed for RL. To capture trained policies, we develop a framework based on an expressive and lossless graph data model that accommodates Temporal Difference Learning and Deep-RL based RL algorithms. Our framework is able to capture arbitrary reward functions that can be composed at inference time. The framework comes with theoretical guarantees and shows that it yields the same result as policies trained from scratch. We design a parameterized algorithm that strikes a balance between efficiency and quality w.r.t cumulative reward. Our experiments with two common RL tasks (query refinement and robot movement) corroborate our theory and show the effectiveness and efficiency of our algorithms.
more »
« less
- Award ID(s):
- 1942913
- PAR ID:
- 10589652
- Publisher / Repository:
- Springer Science + Business Media
- Date Published:
- Journal Name:
- The VLDB Journal
- Volume:
- 34
- Issue:
- 4
- ISSN:
- 1066-8888
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Pedagogical planners can provide adaptive support to students in narrative-centered learning environments by dynamically scaffolding student learning and tailoring problem scenarios. Reinforcement learning (RL) is frequently used for pedagogical planning in narrative-centered learning environments. However, RL-based pedagogical planning raises significant challenges due to the scarcity of data for training RL policies. Most prior work has relied on limited-size datasets and offline RL techniques for policy learning. Unfortunately, offline RL techniques do not support on-demand exploration and evaluation, which can adversely impact the quality of induced policies. To address the limitation of data scarcity and offline RL, we propose INSIGHT, an online RL framework for training data-driven pedagogical policies that optimize student learning in narrative-centered learning environments. The INSIGHT framework consists of three components: a narrative-centered learning environment simulator, a simulated student agent, and an RL-based pedagogical planner agent, which uses a reward metric that is associated with effective student learning processes. The framework enables the generation of synthetic data for on-demand exploration and evaluation of RL-based pedagogical planning. We have implemented INSIGHT with OpenAI Gym for a narrative-centered learning environment testbed with rule-based simulated student agents and a deep Q-learning-based pedagogical planner. Our results show that online deep RL algorithms can induce near-optimal pedagogical policies in the INSIGHT framework, while offline deep RL algorithms only find suboptimal policies even with large amounts of data.more » « less
-
Learning from Demonstration (LfD) is a promising approach to enable Multi-Robot Systems (MRS) to acquire complex skills and behaviors. However, the intricate interactions and coordination challenges in MRS pose significant hurdles for effective LfD. In this paper, we present a novel LfD framework specifically designed for MRS, which leverages visual demonstrations to capture and learn from robot-robot and robot-object interactions. Our framework introduces the concept of Interaction Keypoints (IKs) to transform the visual demonstrations into a representation that facilitates the inference of various skills necessary for the task. The robots then execute the task using sensorimotor actions and reinforcement learning (RL) policies when required. A key feature of our approach is the ability to handle unseen contact-based skills that emerge during the demonstration. In such cases, RL is employed to learn the skill using a classifier-based reward function, eliminating the need for manual reward engineering and ensuring adaptability to environmental changes. We evaluate our framework across a range of mobile robot tasks, covering both behavior-based and contact-based domains. The results demonstrate the effectiveness of our approach in enabling robots to learn complex multi-robot tasks and behaviors from visual demonstrations.more » « less
-
A long-standing question in robot hand design is how accurate tactile sensing must be. This paper uses simulated tactile signals and the reinforcement learning (RL) framework to study the sensing needs in grasping systems. Our first experiment investigates the need for rich tactile sensing in the rewards of RL-based grasp refinement algorithms for multi-fingered robotic hands. We systematically integrate different levels of tactile data into the rewards using analytic grasp stability metrics. We find that combining information on contact positions, normals, and forces in the reward yields the highest average success rates of 95.4% for cuboids, 93.1% for cylinders, and 62.3% for spheres across wrist position errors between 0 and 7 centimeters and rotational errors between 0 and 14 degrees. This contact-based reward outperforms a non-tactile binary-reward baseline by 42.9%. Our follow-up experiment shows that when training with tactile-enabled rewards, the use of tactile information in the control policy’s state vector is drastically reducible at only a slight performance decrease of at most 6.6% for no tactile sensing in the state. Since policies do not require access to the reward signal at test time, our work implies that models trained on tactile-enabled hands are deployable to robotic hands with a smaller sensor suite, potentially reducing cost dramatically.more » « less
-
null (Ed.)Abstract: Identifying critical decisions is one of the most challenging decision-making problems in real-world applications. In this work, we propose a novel Reinforcement Learning (RL) based Long-Short Term Rewards (LSTR) framework for critical decisions identification. RL is a machine learning area concerned with inducing effective decision-making policies, following which result in the maximum cumulative "reward." Many RL algorithms find the optimal policy via estimating the optimal Q-values, which specify the maximum cumulative reward the agent can receive. In our LSTR framework, the "long term" rewards are defined as "Q-values" and the "short term" rewards are determined by the "reward function." Experiments on a synthetic GridWorld game and real-world Intelligent Tutoring System datasets show that the proposed LSTR framework indeed identifies the critical decisions in the sequences. Furthermore, our results show that carrying out the critical decisions alone is as effective as a fully-executed policy.more » « less
