marmotlab / decaying_action_priors
[IROS 2024] DecAP: Decaying Action Priors for Accelerated Learning of Torque-Based Legged Locomotion Policies
☆17Updated 3 weeks ago
Alternatives and similar repositories for decaying_action_priors:
Users that are interested in decaying_action_priors are comparing it to the libraries listed below
- ☆20Updated 5 months ago
- phase-based Observations, Rewards, Coupling Ablation☆39Updated 11 months ago
- Train guide dog controller and force estimator in Isaac Gym and validate in PyBullet☆19Updated last year
- A Python implementation about quadruped locomotion using convex model predictive control (MPC).☆40Updated last year
- Code for our ICRA 2024 paper on learning diverse skills☆20Updated 10 months ago
- ☆40Updated 2 weeks ago
- ☆17Updated 7 months ago
- Project code.☆19Updated 2 weeks ago
- Source code for the paper DiffuseLoco: Real-Time Legged Locomotion Control with Diffusion from Offline Datasets☆49Updated 3 months ago
- ☆65Updated last year
- Torobo models and example scripts in MuJoCo☆55Updated 2 months ago
- Towards better athletic intelligence☆22Updated 8 months ago
- ☆26Updated 3 months ago
- Globally Safe Model-free Exploration of Dynamical Systems☆30Updated 3 months ago
- Learning Agile Quadrupedal Locomotion on Challenging Terrains☆51Updated 10 months ago
- Repository for our paper: Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations Proceedings of the 6th Conferen…☆59Updated 11 months ago
- ☆23Updated 3 months ago
- Humanoid loco-manipulation controller☆30Updated 2 weeks ago
- ☆32Updated last year
- RL training for quadruped robot(mit minicheetah) various gaits in different velocity based on MPC controller.☆16Updated 2 years ago
- Implementation of some core elements of "Learning robust perceptive locomotion for quadrupedal robots in the wild"☆41Updated last year
- ☆64Updated 5 months ago
- Humanoid robot playing balance board in NVIDIA Isaac Gym using PPO.☆14Updated 2 years ago
- A collection of MPC walking scripts with various models☆31Updated 2 weeks ago
- [IROS 2024] LEEPS : Learning End-to-End Legged Perceptive Parkour Skills on Challenging Terrains☆48Updated 7 months ago
- ☆36Updated 11 months ago
- RL code for the paper "OPT-Mimic: Imitation of Optimized Trajectories for Dynamic Quadruped Behaviors"☆20Updated last year
- ☆25Updated last week
- ☆19Updated last month