Hi Kun,
There are various reasons because of which an agent may take longer to converge. Various ways by which a model can be saved, and the training can be resumed can be found in the documentation below:
The reasons why a pre-trained agent can take longer in the same environment are:
- Overfitting a specific set of data
- Different objectives of the agent
- Architectural difference of the neural networks used in the agent
- Exploration vs Exploitation tradeoff
- Incorrectly initialized hyperparameters
Above pointers can be used for diagnosing reasons of a slower convergence of the agent.
Hope this helps.
