Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userModel-Based Offline Planning with Trajectory Pruning
116
0
0.0
(
0
)
Added by
Xianyuan Zhan
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Offline reinforcement learning (RL) enables learning policies using pre-collected datasets without environment interaction, which provides a promising direction to make RL useable in real-world systems. Although recent offline RL studies have achieved much progress, existing methods still face many practical challenges in real-world system control tasks, such as computational restriction during agent training and the requirement of extra control flexibility. Model-based planning framework provides an attractive solution for such tasks. However, most model-based planning algorithms are not designed for offline settings. Simply combining the ingredients of offline RL with existing methods either provides over-restrictive planning or leads to inferior performance. We propose a new light-weighted model-based offline planning framework, namely MOPP, which tackles the dilemma between the restrictions of offline learning and high-performance planning. MOPP encourages more aggressive trajectory rollout guided by the behavior policy learned from data, and prunes out problematic trajectories to avoid potential out-of-distribution samples. Experimental results show that MOPP provides competitive performance compared with existing model-based offline planning and RL approaches, and allows easy adaptation to varying objectives and extra constraints.
rate research
Read More
Offline learning is a key part of making reinforcement learning (RL) useable in real systems. Offline RL looks at scenarios where there is data from a systems operation, but no direct access to the system when learning a policy. Recent work on training RL policies from offline data has shown results both with model-free policies learned directly from the data, or with planning on top of learnt models of the data. Model-free policies tend to be more performant, but are more opaque, harder to command externally, and less easy to integrate into larger systems. We propose an offline learner that generates a model that can be used to control the system directly through planning. This allows us to have easily controllable policies directly from data, without ever interacting with the system. We show the performance of our algorithm, Model-Based Offline Planning (MBOP) on a series of robotics-inspired tasks, and demonstrate its ability leverage planning to respect environmental constraints. We are able to find near-optimal polices for certain simulated systems from as little as 50 seconds of real-time system interaction, and create zero-shot goal-conditioned policies on a series of environments. An accompanying video can be found here: https://youtu.be/nxGGHdZOFts
We present a framework for bi-level trajectory optimization in which a systems dynamics are encoded as the solution to a constrained optimization problem and smooth gradients of this lower-level problem are passed to an upper-level trajectory optimizer. This optimization-based dynamics representation enables constraint handling, additional variables, and non-smooth forces to be abstracted away from the upper-level optimizer, and allows classical unconstrained optimizers to synthesize trajectories for more complex systems. We provide a path-following method for efficient evaluation of constrained dynamics and utilize the implicit-function theorem to compute smooth gradients of this representation. We demonstrate the framework by modeling systems from locomotion, aerospace, and manipulation domains including: acrobot with joint limits, cart-pole subject to Coulomb friction, Raibert hopper, rocket landing with thrust limits, and planar-push task with optimization-based dynamics and then optimize trajectories using iterative LQR.
New autonomous driving technologies are emerging every day and some of them have been commercially applied in the real world. While benefiting from these technologies, autonomous trucks are facing new challenges in short-term maintenance planning, which directly influences the truck operators profit. In this paper, we implement a vehicle health management system by addressing the maintenance planning issues of autonomous trucks on a transport mission. We also present a maintenance planning model using a risk-based decision-making method, which identifies the maintenance decision with minimal economic risk of the truck company. Both availability losses and maintenance costs are considered when evaluating the economic risk. We demonstrate the proposed model by numerical experiments illustrating real-world scenarios. In the experiments, compared to three baseline methods, the expected economic risk of the proposed method is reduced by up to $47%$. We also conduct sensitivity analyses of different model parameters. The analyses show that the economic risk significantly decreases when the estimation accuracy of remaining useful life, the maximal allowed time of delivery delay before order cancellation, or the number of workshops increases. The experiment results contribute to identifying future research and development attentions of autonomous trucks from an economic perspective.
We introduce a prioritized system-optimal algorithm for mandatory lane change (MLC) behavior of connected and automated vehicles (CAV) from a dedicated lane. Our approach applies a cooperative lane change that prioritizes the decisions of lane changing vehicles which are closer to the end of the diverging zone (DZ), and optimizes the predicted total system travel time. Our experiments on synthetic data show that the proposed algorithm improves the traffic network efficiency by attaining higher speeds in the dedicated lane and earlier MLC positions while ensuring a low computational time. Our approach outperforms the traditional gap acceptance model.
In this paper, we consider a wireless uplink transmission scenario in which an unmanned aerial vehicle (UAV) serves as an aerial base station collecting data from ground users. To optimize the expected sum uplink transmit rate without any prior knowledge of ground users (e.g., locations, channel state information and transmit power), the trajectory planning problem is optimized via the quantum-inspired reinforcement learning (QiRL) approach. Specifically, the QiRL method adopts novel probabilistic action selection policy and new reinforcement strategy, which are inspired by the collapse phenomenon and amplitude amplification in quantum computation theory, respectively. Numerical results demonstrate that the proposed QiRL solution can offer natural balancing between exploration and exploitation via ranking collapse probabilities of possible actions, compared to the traditional reinforcement learning approaches which are highly dependent on tuned exploration parameters.
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
