Hello there, I made a custom environment (with Gym API) and I was able to use Rllib for training agents in this environment. I wrote a rule-based "expert " that does not utilize a neural network to sample its actions. I wish to sample trajectories from this “expert” then warm-start my RL agents usi…

Hi @mickelliu and welcome, so to sample data from the expert interactions with your environment I would write a custom policy as shown in the documentation . Then to produce an offline dataset for training you need to use the offline dataset API . Basically, you create from your Custom Policy a Trai…

Sample Rule-Based Expert Demonstrations in Rllib

RLlib

Lars_Simon_Zehnder July 29, 2021, 6:03pm 3

Also, maybe this thread helps you.

1 Like

Topic		Replies	Views
Implementing Jump Start Reinforcement Learning in RLLib RLlib	8	1174	May 27, 2022
Offline data with self made dataset RLlib	1	268	June 7, 2023
[RLlib] Make it easier to play trained policies RLlib	2	771	June 3, 2021
Pre-train a model with baseline policy Offline RL	0	193	February 6, 2024
Behavior Cloning through custom env RLlib	4	508	August 13, 2021

Sample Rule-Based Expert Demonstrations in Rllib

Related topics