reinforcement-learning-algorithms icon indicating copy to clipboard operation
reinforcement-learning-algorithms copied to clipboard

SAC Agent still wrong with "tuple index out of range" use "MountainCar-v0"

Open StewartTsai opened this issue 3 years ago • 1 comments

I try to use "MountainCar-v0" env in sac agent but still wrong with "tuple index out of range" Could you tell me how to fix it ? Thanks

Traceback (most recent call last): File "D:\RL_library/sac/train.py", line 14, in sac_trainer = sac_agent(env, args) File "D:RL_library\sac\sac_agent.py", line 30, in init self.qf1 = flatten_mlp(self.env.observation_space.shape[0], self.args.hidden_size, self.env.action_space.shape[0]) IndexError: tuple index out of range

StewartTsai avatar Feb 18 '22 06:02 StewartTsai

@StewartTsai Hi - my SAC implementation aims to solve the MuJoCo tasks with continuous control, thus I haven't tested MountainCar-v0 in the current version. But I will fix this problem in these days and notify you in this issue.

TianhongDai avatar Feb 18 '22 19:02 TianhongDai