Error, when ran for other environments like reacher-v1.

stevenpjg / ddpg-aigym

Continuous control with deep reinforcement learning - Deep Deterministic Policy Gradient (DDPG) algorithm implemented in OpenAI Gym environments

MIT License

272 stars 74 forks source link

Error, when ran for other environments like reacher-v1. #5

Closed sarvghotra closed 8 years ago

sarvghotra commented 8 years ago

I tried to run this code for Reacher-v1 and Swimmer-v1 but it threw an error due to this line. ValueError: total size of new array must be unchanged

Could you please also explain why do you even need this step for InvertedPendulum ?

stevenpjg commented 8 years ago

Fixed! I would recommend you to add one more wrapper to scale your reward, as reacher and swimmer takes so long to train.

This is the step where action is computed using actor network model.