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
18 Nov 01, 2022
51 Nov 29, 2022
46 Jul 06, 2022
7 Oct 23, 2021
25 Nov 30, 2022
2.8k Dec 30, 2022
1 Jan 15, 2022
3 Jan 23, 2022
18 Aug 11, 2022
0 Jun 25, 2021
26 Oct 18, 2022
7 Jan 03, 2023
10 Dec 06, 2022
2 Aug 08, 2022
4k Jan 02, 2023
643 Dec 30, 2022
10 Jun 30, 2022
9 Nov 01, 2022
7 Aug 16, 2022
42 Jan 04, 2023