HIGL
This is a PyTorch implementation for our paper: Landmark-Guided Subgoal Generation in Hierarchical Reinforcement Learning (NeurIPS 2021).
Our code is based on official implementation of HRAC (NeurIPS 2020) and Map-planner (NeurIPS 2019)
Installation
conda create -n higl python=3.6
conda activate higl
./install_all.sh
Also, to run the MuJoCo experiments, a license is required (see here).
Usage
Training & Evaluation
- Point Maze
./scripts/point_maze_sparse.sh ${reward_shaping} ${timesteps} ${gpu} ${seed}
./scripts/point_maze_sparse.sh dense 5e5 0 2
./scripts/point_maze_sparse.sh sparse 5e5 0 2
- Ant Maze (U-shape)
./scripts/higl_ant_maze_u.sh ${reward_shaping} ${timesteps} ${gpu} ${seed}
./scripts/higl_ant_maze_u.sh dense 10e5 0 2
./scripts/higl_ant_maze_u.sh sparse 10e5 0 2
- Ant Maze (W-shape)
./scripts/higl_ant_maze_w.sh ${reward_shaping} ${timesteps} ${gpu} ${seed}
./scripts/higl_ant_maze_w.sh dense 10e5 0 2
./scripts/higl_ant_maze_w.sh sparse 10e5 0 2
- Reacher & Pusher
./scripts/higl_fetch.sh ${env} ${timesteps} ${gpu} ${seed}
./scripts/higl_fetch.sh Reacher3D-v0 5e5 0 2
./scripts/higl_fetch.sh Pusher-v0 10e5 0 2
- Stochastic Ant Maze (U-shape)
./scripts/higl_ant_maze_u_stoch.sh ${reward_shaping} ${timesteps} ${gpu} ${seed}
./scripts/higl_ant_maze_u_stoch.sh dense 10e5 0 2
./scripts/higl_ant_maze_u_stoch.sh sparse 10e5 0 2
6 Nov 15, 2022
134 Jul 10, 2022
12 Nov 30, 2022
3 Aug 24, 2022
72 Dec 20, 2022
75 Dec 16, 2022
12 Sep 26, 2022
5.3k Dec 28, 2022
28 Dec 13, 2022
2 Mar 12, 2022
19 Dec 10, 2022
66 Dec 26, 2022
330 Dec 11, 2022
2 Dec 08, 2021
1 Jan 25, 2022
4 Aug 13, 2022
251 Dec 08, 2022
1 Jan 05, 2022
1.3k Dec 28, 2022
154 Jan 04, 2023