An official website of the United States government
Learning from active human involvement enables the human subject to actively intervene and demonstrate to the AI agent during training. The interaction and corrective feedback from human brings safety and AI alignment to the learning process. In this work, we propose a new reward-free active human involvement method called Proxy Value Propagation for policy optimization. Our key insight is that a proxy value function can be designed to express human intents, wherein state- action pairs in the human demonstration are labeled with high values, while those agents’ actions that are intervened receive low values. Through the TD-learning framework, labeled values of demonstrated state-action pairs are further propagated to other unlabeled data generated from agents’ exploration. The proxy value function thus induces a policy that faithfully emulates human behaviors. Human- in-the-loop experiments show the generality and efficiency of our method. With minimal modification to existing reinforcement learning algorithms, our method can learn to solve continuous and discrete control tasks with various human control devices, including the challenging task of driving in Grand Theft Auto V. Demo video and code are available at: https://metadriverse.github.io/pvp.
more »
« less
Avoiding Lingering in Learning Active Recognition by Adversarial Disturbance
This paper considers the active recognition scenario, where the agent is empowered to intelligently acquire observations for better recognition. The agents usually compose two modules, i.e., the policy and the recognizer, to select actions and predict the category. While using ground-truth class labels to supervise the recognizer, the policy is typically updated with rewards determined by the current in-training recognizer, like whether achieving correct predictions. However, this joint learning process could lead to unintended solutions, like a collapsed policy that only visits views that the recognizer is already sufficiently trained to obtain rewards, which harms the generalization ability. We call this phenomenon lingering to depict the agent being reluctant to explore challenging views during training. Existing approaches to tackle the exploration-exploitation trade-off could be ineffective as they usually assume reliable feedback during exploration to update the estimate of rarely-visited states. This assumption is invalid here as the reward from the recognizer could be insufficiently trained.To this end, our approach integrates another adversarial policy to constantly disturb the recognition agent during training, forming a competing game to promote active explorations and avoid lingering. The reinforced adversary, rewarded when the recognition fails, contests the recognition agent by turning the camera to challenging observations. Extensive experiments across two datasets validate the effectiveness of the proposed approach regarding its recognition performances, learning efficiencies, and especially robustness in managing environmental noises.
more »
« less
- PAR ID:
- 10464213
- Date Published:
- Journal Name:
- IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
- Page Range / eLocation ID:
- 4601 to 4610
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)While Deep Reinforcement Learning has emerged as a de facto approach to many complex experience-driven networking problems, it remains challenging to deploy DRL into real systems. Due to the random exploration or half-trained deep neural networks during the online training process, the DRL agent may make unexpected decisions, which may lead to system performance degradation or even system crash. In this paper, we propose PnP-DRL, an offline-trained, plug and play DRL solution, to leverage the batch reinforcement learning approach to learn the best control policy from pre-collected transition samples without interacting with the system. After being trained without interaction with systems, our Plug and Play DRL agent will start working seamlessly, without additional exploration or possible disruption of the running systems. We implement and evaluate our PnP-DRL solution on a prevalent experience-driven networking problem, Dynamic Adaptive Streaming over HTTP (DASH). Extensive experimental results manifest that 1) The existing batch reinforcement learning method has its limits; 2) Our approach PnP-DRL significantly outperforms classical adaptive bitrate algorithms in average user Quality of Experience (QoE); 3) PnP-DRL, unlike the state-of-the-art online DRL methods, can be off and running without learning gaps, while achieving comparable performances.more » « less
-
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.more » « less
-
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.more » « less
-
null (Ed.)In this work, we consider learning a wafer plot recognizer where only one training sample is available. We introduce an approach called Manifestation Learning to enable the learning. The underlying technology utilizes the Variational AutoEncoder (VAE) approach to construct a so-called Manifestation Space. The training sample is projected into this space and the recognition is achieved through a pre-trained model in the space. Using wafer probe test data from an automotive product line, this paper explains the learning approach, its feasibility and limitation.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/WACV56688.2023.00459
