Lin

Last seen: 7 months ago | Active since 2023

Followers: 0 Following: 0

Statistics

Feeds

Question

In TrainMBPOAgentToBalanceCartPoleSystemExample/ cartPoleRewardFunction ，（nextObs）is what？
function reward = cartPoleRewardFunction(obs,action,nextObs) % Compute reward value based on the next observation. if is...

11 months ago | 1 answer | 0

1

answer

Question

References to multi-agent reinforcement learning schemes in the reinforcement learning toolbox
Can somebody provide several references on multi-agent reinforcement learning schemes in reinforcement learning toolbox？

1 year ago | 1 answer | 0

1

answer

Question

The simulation time set by reinforcement learning is inconsistent with the training time
The simulation time set by reinforcement learning is inconsistent with the training time。

1 year ago | 1 answer | 0

1

answer

Question

Must centralized trained groups of agents have the same action specification?
Hello: numObservations = 4; observationInfo = rlNumericSpec([numObservations 1],... 'LowerLimit',[-inf -inf -inf -inf]'...

1 year ago | 1 answer | 0

1

answer

Question

How to make the agent automatically pause after training to a certain number of turns
How to make the agent automatically pause after training to a certain number of turns.I want to stop the agent and then bring in...

2 years ago | 2 answers | 0

2

answers

Question

When training reinforcement Learning toolbox, how can we transfer EpisodeQ0 into Simulink in real time
When training reinforcement Learning toolbox, how can we transfer EpisodeQ0 into Simulink in real time,I want to use the value o...

2 years ago | 1 answer | 0

1

answer