Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[RLlib] Don't add a cpu to bundle for learner when using gpu #35529

Merged
Merged
Changes from 1 commit
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
Reduce num rollout workers
Signed-off-by: Avnish <[email protected]>
  • Loading branch information
avnishn committed May 23, 2023
commit b3b7c8f801b7709ab3ae50bfa38b4fe390515fbf
2 changes: 1 addition & 1 deletion rllib/examples/learner/multi_agent_cartpole_ppo.py
Original file line number Diff line number Diff line change
Expand Up @@ -95,7 +95,7 @@ def policy_mapping_fn(agent_id, episode, worker, **kwargs):

config = (
PPOConfig()
.rollouts(rollout_fragment_length="auto", num_rollout_workers=6)
.rollouts(rollout_fragment_length="auto", num_rollout_workers=3)
.environment(MultiAgentCartPole, env_config={"num_agents": args.num_agents})
.framework(args.framework)
.training(num_sgd_iter=10, sgd_minibatch_size=2**9, train_batch_size=2**12)
Expand Down
Loading