ray/rllib/tuned_examples/atari-ppo.yaml
Eric Liang dd70720578
[rllib] Rename sample_batch_size => rollout_fragment_length (#7503)
* bulk rename

* deprecation warn

* update doc

* update fig

* line length

* rename

* make pytest comptaible

* fix test

* fi sys

* rename

* wip

* fix more

* lint

* update svg

* comments

* lint

* fix use of batch steps
2020-03-14 12:05:04 -07:00

27 lines
768 B
YAML

# Runs on a single g3.16xl node
# See https://github.com/ray-project/rl-experiments for results
atari-ppo:
env:
grid_search:
- BreakoutNoFrameskip-v4
- BeamRiderNoFrameskip-v4
- QbertNoFrameskip-v4
- SpaceInvadersNoFrameskip-v4
run: PPO
config:
lambda: 0.95
kl_coeff: 0.5
clip_rewards: True
clip_param: 0.1
vf_clip_param: 10.0
entropy_coeff: 0.01
train_batch_size: 5000
rollout_fragment_length: 100
sgd_minibatch_size: 500
num_sgd_iter: 10
num_workers: 10
num_envs_per_worker: 5
batch_mode: truncate_episodes
observation_filter: NoFilter
vf_share_layers: true
num_gpus: 1