Ray
TrajectoryTracking with RLLIB
RLlib
mannyv
November 11, 2021, 10:15pm
10
@mg64ve
You can a avoid the issue even in the current version by doing 2 things.
Set the config[“simple_optimizer”]=True
Set sgd_minibatch_size > max_seq_len
1 Like
Use Policy_Trainer with TensorBoard
show post in topic
Related Topics
Topic
Replies
Views
Activity
Not Sure Which RLlib Algorithm To Use
RLlib
5
550
April 27, 2021
My RLlib implementation seems to compute random actions
RLlib
4
773
February 15, 2022
[rllib] Retrieve and modify the computed discrete action logits to PPO agent
RLlib
6
592
May 5, 2021
Multi-agent setting different step sizes for agents and how actions are passed?
RLlib
2
399
April 26, 2022
Reproducing results from stablebaselines 3
RLlib
2
550
August 6, 2021