1
0
mirror of https://github.com/gryf/coach.git synced 2025-12-17 19:20:19 +01:00
Files
coach/benchmarks/ddpg_her
2018-08-13 17:11:34 +03:00
..
2018-08-13 17:11:34 +03:00

DDPG with Hindsight Experience Replay

Each experiment uses 3 seeds. The parameters used for DDPG HER are the same parameters as described in the following paper.

Fetch Reach DDPG HER - single worker

python3 coach.py -p Fetch_DDPG_HER_baselines -lvl reach
Fetch DDPG HER Reach 1 Worker

Fetch Push DDPG HER - 8 workers

python3 coach.py -p Fetch_DDPG_HER_baselines -lvl push -n 8
Fetch DDPG HER Push 8 Worker

Fetch Slide DDPG HER - 8 workers

python3 coach.py -p Fetch_DDPG_HER_baselines -lvl slide -n 8
Fetch DDPG HER Slide 8 Worker

Fetch Pick And Place DDPG HER - 8 workers

python3 coach.py -p Fetch_DDPG_HER -lvl pick_and_place -n 8
Fetch DDPG HER Pick And Place 8 Workers