Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userMeta-Adversarial Inverse Reinforcement Learning for Decision-making Tasks
137
0
0.0
(
0
)
Added by
Pin Wang
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Learning from demonstrations has made great progress over the past few years. However, it is generally data hungry and task specific. In other words, it requires a large amount of data to train a decent model on a particular task, and the model often fails to generalize to new tasks that have a different distribution. In practice, demonstrations from new tasks will be continuously observed and the data might be unlabeled or only partially labeled. Therefore, it is desirable for the trained model to adapt to new tasks that have limited data samples available. In this work, we build an adaptable imitation learning model based on the integration of Meta-learning and Adversarial Inverse Reinforcement Learning (Meta-AIRL). We exploit the adversarial learning and inverse reinforcement learning mechanisms to learn policies and reward functions simultaneously from available training tasks and then adapt them to new tasks with the meta-learning framework. Simulation results show that the adapted policy trained with Meta-AIRL can effectively learn from limited number of demonstrations, and quickly reach the performance comparable to that of the experts on unseen tasks.
rate research
Read More
Meta-reinforcement learning (meta-RL) aims to learn from multiple training tasks the ability to adapt efficiently to unseen test tasks. Despite the success, existing meta-RL algorithms are known to be sensitive to the task distribution shift. When the test task distribution is different from the training task distribution, the performance may degrade significantly. To address this issue, this paper proposes Model-based Adversarial Meta-Reinforcement Learning (AdMRL), where we aim to minimize the worst-case sub-optimality gap -- the difference between the optimal return and the return that the algorithm achieves after adaptation -- across all tasks in a family of tasks, with a model-based approach. We propose a minimax objective and optimize it by alternating between learning the dynamics model on a fixed task and finding the adversarial task for the current model -- the task for which the policy induced by the model is maximally suboptimal. Assuming the family of tasks is parameterized, we derive a formula for the gradient of the suboptimality with respect to the task parameters via the implicit function theorem, and show how the gradient estimator can be efficiently implemented by the conjugate gradient method and a novel use of the REINFORCE estimator. We evaluate our approach on several continuous control benchmarks and demonstrate its efficacy in the worst-case performance over all tasks, the generalization power to out-of-distribution tasks, and in training and test time sample efficiency, over existing state-of-the-art meta-RL algorithms.
Reinforcement learning typically assumes that the state update from the previous actions happens instantaneously, and thus can be used for making future decisions. However, this may not always be true. When the state update is not available, the decision taken is partly in the blind since it cannot rely on the current state information. This paper proposes an approach, where the delay in the knowledge of the state can be used, and the decisions are made based on the available information which may not include the current state information. One approach could be to include the actions after the last-known state as a part of the state information, however, that leads to an increased state-space making the problem complex and slower in convergence. The proposed algorithm gives an alternate approach where the state space is not enlarged, as compared to the case when there is no delay in the state update. Evaluations on the basic RL environments further illustrate the improved performance of the proposed algorithm.
Knowledge transfer is a promising concept to achieve real-time decision-making for autonomous vehicles. This paper constructs a transfer deep reinforcement learning framework to transform the driving tasks in inter-section environments. The driving missions at the un-signalized intersection are cast into a left turn, right turn, and running straight for automated vehicles. The goal of the autonomous ego vehicle (AEV) is to drive through the intersection situation efficiently and safely. This objective promotes the studied vehicle to increase its speed and avoid crashing other vehicles. The decision-making pol-icy learned from one driving task is transferred and evaluated in another driving mission. Simulation results reveal that the decision-making strategies related to similar tasks are transferable. It indicates that the presented control framework could reduce the time consumption and realize online implementation.
We introduce a unified probabilistic framework for solving sequential decision making problems ranging from Bayesian optimisation to contextual bandits and reinforcement learning. This is accomplished by a probabilistic model-based approach that explains observed data while capturing predictive uncertainty during the decision making process. Crucially, this probabilistic model is chosen to be a Meta-Learning system that allows learning from a distribution of related problems, allowing data efficient adaptation to a target task. As a suitable instantiation of this framework, we explore the use of Neural processes due to statistical and computational desiderata. We apply our framework to a broad range of problem domains, such as control problems, recommender systems and adversarial attacks on RL agents, demonstrating an efficient and general black-box learning approach.
Thompson sampling and other Bayesian sequential decision-making algorithms are among the most popular approaches to tackle explore/exploit trade-offs in (contextual) bandits. The choice of prior in these algorithms offers flexibility to encode domain knowledge but can also lead to poor performance when misspecified. In this paper, we demonstrate that performance degrades gracefully with misspecification. We prove that the expected reward accrued by Thompson sampling (TS) with a misspecified prior differs by at most $tilde{mathcal{O}}(H^2 epsilon)$ from TS with a well specified prior, where $epsilon$ is the total-variation distance between priors and $H$ is the learning horizon. Our bound does not require the prior to have any parametric form. For priors with bounded support, our bound is independent of the cardinality or structure of the action space, and we show that it is tight up to universal constants in the worst case. Building on our sensitivity analysis, we establish generic PAC guarantees for algorithms in the recently studied Bayesian meta-learning setting and derive corollaries for various families of priors. Our results generalize along two axes: (1) they apply to a broader family of Bayesian decision-making algorithms, including a Monte-Carlo implementation of the knowledge gradient algorithm (KG), and (2) they apply to Bayesian POMDPs, the most general Bayesian decision-making setting, encompassing contextual bandits as a special case. Through numerical simulations, we illustrate how prior misspecification and the deployment of one-step look-ahead (as in KG) can impact the convergence of meta-learning in multi-armed and contextual bandits with structured and correlated priors.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
