The filtering is incorrectly clipping the action values to between [-1,1].
Line 70 of FilteredEnv:
ac_f = np.clip(self.filter_action(action),self.action_space.low,self.action_space.high)
self.action_space.low and self.action_space.high are arrays with value -1 and 1:
self.action_space = gym.spaces.Box(-np.ones_like(acsp.high),np.ones_like(acsp.high))
self.filter_action(action) correctly converts to the range of the environment (e.g., in a 1D case) from [-1,1] to [lower bound, upper bound], but then it clips the value to be between [-1,1], when it should really clip it to be between [lower bound, upper bound].
The filtering is incorrectly clipping the action values to between [-1,1].
Line 70 of FilteredEnv:
self.action_space.lowandself.action_space.highare arrays with value -1 and 1:self.filter_action(action)correctly converts to the range of the environment (e.g., in a 1D case) from [-1,1] to [lower bound, upper bound], but then it clips the value to be between [-1,1], when it should really clip it to be between [lower bound, upper bound].