mirror of
https://github.com/vale981/ray
synced 2025-03-06 18:41:40 -05:00
14 lines
418 B
YAML
14 lines
418 B
YAML
|
# To generate training data, first run:
|
||
|
|
# $ ./train.py --run=PPO --env=CartPole-v0 \
|
||
|
|
# --stop='{"timesteps_total": 50000}' \
|
||
|
|
# --config='{"output": "/tmp/out", "batch_mode": "complete_episodes"}'
|
||
|
|
cartpole-marwil:
|
||
|
|
env: CartPole-v0
|
||
|
|
run: MARWIL
|
||
|
|
stop:
|
||
|
|
timesteps_total: 500000
|
||
|
|
config:
|
||
|
|
beta:
|
||
|
|
grid_search: [0, 1] # compare IL (beta=0) vs MARWIL
|
||
|
|
input: /tmp/out
|