Improved Activity Forecasting for Generating Trajectories
On the map: Offline RL and imitation learning from data → Inverse reinforcement learning
Abstract (arXiv)
An efficient inverse reinforcement learning for generating trajectories is proposed based of 2D and 3D activity forecasting. We modify reward function with Lp norm and propose convolution into value iteration steps, which is called convolutional value iteration. Experimental results with seabird trajectories (43 for training and 10 for test), our method is best in terms of MHD error and performs fastest. Generated trajectories for interpolating missing parts of trajectories look much similar to real seabird trajectories than those by the previous works.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Inverse reinforcement learning, one of 13 directions in Offline RL and imitation learning from data. First posted on arXiv 12 Dec 2019.
Builds on
No reference list yet.
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2020Trajectory Forecasts in Unknown Environments Conditioned on Grid-Based Plans
- 2022End-to-End Trajectory Distribution Prediction Based on Occupancy Grid Maps
- 2019Inverse Reinforcement Learning with Missing Data
- 2019Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations
- 2020Efficient Exploration of Reward Functions in Inverse Reinforcement Learning via Bayesian Optimization
- 2025Foresight in Motion: Reinforcing Trajectory Prediction with Reward Heuristics
- 2026Not All Rollouts Are Worth Learning: On Trajectory Valuation for Post-Training Reinforcement Learning
- 2023Distance-rank Aware Sequential Reward Learning for Inverse Reinforcement Learning with Sub-optimal Demonstrations