A Unity ID allows you to buy and/or subscribe to Unity products and services, shop in the Asset Store and participate in the Unity community.
Separate names with a comma.
No problems because I'm not using the saved buffer (just tested it for understanding). But if I'd use it I would expect a saved buffer at end of...
push (new video about the ML-Agents Hyperparameters)
When interrupting training, it works fine. Just experienced it when I finished a training run, without interruption. I'd still expect that the...
Hey, just trained the PushBlock example environment with 'save_replay_buffer' set to 'true'. During training the 'last_replay_buffer.hdf5'...
https://github.com/Unity-Technologies/ml-agents/pull/4252
Okay :) I can make a PR - will post the PR link here during the next hour
Hey! I was just wondering if I understood the buffer_size parameter correctly. The documentation confused me somehow. Documentation (default =...
push (next video about the Hyperparameters for PPO and SAC likely by end of July)
From what I know, the size of the observation space has to be of a fixed size. I think it is an algorithmic limitation for both PPO and SAC.
does it help setting it to constant?
Maybe it's because of the lack of exploration at the end of training with an environment that still changes to unknown shapes? Are you using PPO...
Entropy looks good but from my understanding I would expect the reward to increase when the entropy goes down. Is there any randomness in your...
Also make sure that the name you set in the Behavior Parameters -> Behavior Name is the same that you defined in the config. Otherwise it will...
Thats interesting. Hopefully someone from the dev team can help you out!
do you have set a max_step for an episode or is it a continuous environment which does not reset? I guess the agent encountered a situation that...
I am quite sure that the agent needs to explore more with the complex observations because there are more possibilities, so it takes longer to...
I had the same issue. Used Release 3 and the default 3DBall environment with SAC. Only changed the max_steps to 1 million. Occurred at around 700k...
added a new video about Tensorboard with ML-Agents
Good to know. Glad that it's working for you now! Enjoy ML-Agents :)
That goes beyond my knowledge to be honest, so I hope someone else can help you. Chances are quite big that it is not working cause of missing...