Hi, When using a dqn agents (or any other relevant algorithms for that matter) - is there a way that I can manipulate the agent’s memory buffer during the training? *By manipulation I intend to adding or removing transitions from/to the buffer.

Hi @Ofir_Abu , this manipulation is certainly not trivial. As you can see in the source code , the ReplayBuffer holds in _storage a list of SampleBatches that contain the experiences from the environment. This means, you either need to add (by using add() or remove SampleBatches directly from this b…

Accessing the memory buffer dqn

RLlib

Roller44 November 10, 2021, 3:50pm 5

Yes. Sorry. I have started a new topic. Here is the link, if you are interested in it.

Topic		Replies	Views
Sample form the reply buffer sequentially in DQN RLlib	1	213	June 27, 2022
Offline training using previous obs+action=reward tuples RLlib	1	307	May 24, 2021
Rllib trainig step customize RLlib	6	557	March 31, 2021
'MultiAgentBatch' object has no attribute 'get' when using DQN and storing sequences in the Replay Buffer Debugging and performance tuning	0	118	May 11, 2024
Can i check the Replay buffer? RLlib	4	382	July 27, 2021

Accessing the memory buffer dqn

Related topics