[HTML][HTML] Optimizing trajectories for highway driving with offline reinforcement learning
B Mirchevska, M Werling, J Boedecker - Frontiers in Future …, 2023 - frontiersin.org
… propose a Reinforcement Learning-based approach, which learns target trajectory parameters
for fully autonomous driving on highways. The trained agent outputs continuous trajectory …
for fully autonomous driving on highways. The trained agent outputs continuous trajectory …
Offline reinforcement learning as one big sequence modeling problem
… When the goal is to reproduce the distribution of trajectories in the training data, we can
optimize directly for the probability of a trajectory τ. This situation matches the goal of sequence …
optimize directly for the probability of a trajectory τ. This situation matches the goal of sequence …
[PDF][PDF] A Trajectory Perspective on the Role of Data Sampling Techniques in Offline Reinforcement Learning
… offline trajectory data, we investigate the impact of data sampling processes on offline RL
algorithms from a trajectory … In this section, we evaluate PTR, which optimizes the trajectory …
algorithms from a trajectory … In this section, we evaluate PTR, which optimizes the trajectory …
Critic-guided decision transformer for offline reinforcement learning
… optimal and suboptimal trajectories without predefined returns, often resulting in suboptimal
policies that mirror the distribution of the training data. To overcome the limitations of IL, …
policies that mirror the distribution of the training data. To overcome the limitations of IL, …
Beyond uniform sampling: Offline reinforcement learning with imbalanced datasets
… over the average return of trajectories in the dataset. We … offline RL algorithms of staying
close to the trajectories in the dataset. If the dataset primarily consists of sub-optimal trajectories, …
close to the trajectories in the dataset. If the dataset primarily consists of sub-optimal trajectories, …
Safe offline reinforcement learning with real-time budget constraints
… To model the optimal trajectory distribution wrt a certain … To obtain the optimal trajectory
distribution in Theorem 4.1, … 2022), a recently proposed trajectory optimization framework that …
distribution in Theorem 4.1, … 2022), a recently proposed trajectory optimization framework that …
Lapo: Latent-variable advantage-weighted policy optimization for offline reinforcement learning
… In this paper, we study an offline RL setup for learning from heterogeneous datasets where
trajectories are collected using policies with different purposes, leading to a multi-modal data …
trajectories are collected using policies with different purposes, leading to a multi-modal data …
Offline reinforcement learning with implicit q-learning
… We examine domains that contain near-optimal trajectories, where single-step methods
perform well, as well as domains with no optimal trajectories at all, which require multi-step …
perform well, as well as domains with no optimal trajectories at all, which require multi-step …
Offline reinforcement learning: Tutorial, review, and perspectives on open problems
… Another way to optimize the reinforcement learning objective … to then recover a near-optimal
policy. A value function provides … sample new trajectories from πβ, while old trajectories are …
policy. A value function provides … sample new trajectories from πβ, while old trajectories are …
A survey on offline reinforcement learning: Taxonomy, review, and open problems
RF Prudencio, MROA Maximo… - … Networks and Learning …, 2023 - ieeexplore.ieee.org
… ] and trajectory optimization [27… with learning an optimal policy and an optimal trajectory
distribution, respectively. Currently, a limited number of works have reviewed the field of offline …
distribution, respectively. Currently, a limited number of works have reviewed the field of offline …
相关搜索
- open problems offline reinforcement learning
- policy optimization for offline reinforcement learning
- trust region optimization offline reinforcement learning
- multi-task offline reinforcement learning
- sequence modeling problem offline reinforcement learning
- reward augmentation offline reinforcement learning
- latent diffusion offline reinforcement learning
- decision transformer offline reinforcement learning
- three sentences offline reinforcement learning
- actor critic offline reinforcement learning
- data rebalancing offline reinforcement learning
- latent action space offline reinforcement learning
- hyperparameter selection offline reinforcement learning
- minimalist approach offline reinforcement learning
- exploratory data offline reinforcement learning
- offline safe reinforcement learning