Please explain the constraints

Please explain the constraints that need to be satisfied along with maximizing the rewards. What does info['constraint values'] mean?

Hello @MukilSaravanan

are is this a question relating the IROS 2022 competition?

The constraints are specified in the YAML files, e.g.

safe-control-gym/competition/level3.yaml

Lines 128 to 162 in a0e7fa2

    
           # Constraints 
        
           constraints: 
        
             # Input constraints 
        
             - constraint_form: default_constraint 
        
               constrained_variable: input 
        
             # State constraints 
        
             - constraint_form: bounded_constraint 
        
               constrained_variable: state 
        
               active_dims: [0, 2, 4] # The uncommented entries in the upper_bounds/lower_bounds vectors below 
        
               upper_bounds: 
        
               - 3     # x 
        
               # - 100 # x_dot 
        
               - 3     # y 
        
               # - 100 # y_dot 
        
               - 2     # z 
        
               # - 100 # z_dot 
        
               # - 3   # phi 
        
               # - 3   # theta 
        
               # - 3   # psi 
        
               # - 10  # p 
        
               # - 10  # q 
        
               # - 10  # r 
        
               lower_bounds: 
        
               - -3     # x 
        
               # - -100 # x_dot 
        
               - -3     # y 
        
               # - -100 # y_dot 
        
               - -0.1   # z 
        
               # - -100 # z_dot 
        
               # - -3   # phi 
        
               # - -3   # theta 
        
               # - -3   # psi 
        
               # - -10  # p 
        
               # - -10  # q 
        
               # - -10  # r

simply means that there are upper and lower bound for the input (identical to the action_space) and the x, y, z position of the Crazyflies (bounding it to be within a flyable arena of 6 by 6 by 2.1 meters)

info['constraint values'] are the numerical evaluations of those constraints (meaning that any negative value in that entry of the dictionary indicates a violation.

I'm also tagging @adamhall if you have further implementation-specific questions.

info['constraint values'] are the numerical evaluations of those constraints (meaning that any negative value in that entry of the dictionary indicates a violation.

It's actually the other way. ie, if any of those numerical evaluations of constraints is positive, it is said to be violating

info['constraint values'] are the numerical evaluations of those constraints (meaning that any negative value in that entry of the dictionary indicates a violation.

It's actually the other way. ie, if any of those numerical evaluations of constraints is positive, it is said to be violating

I'm sure you're right (@adamhall can confirm or refute), I don't remember the sign convention by heart.
The single boolean in info[constraint_violation] is intended to avoid any ambiguity.

	# Constraints
	constraints:
	# Input constraints
	- constraint_form: default_constraint
	constrained_variable: input
	# State constraints
	- constraint_form: bounded_constraint
	constrained_variable: state
	active_dims: [0, 2, 4] # The uncommented entries in the upper_bounds/lower_bounds vectors below
	upper_bounds:
	- 3 # x
	# - 100 # x_dot
	- 3 # y
	# - 100 # y_dot
	- 2 # z
	# - 100 # z_dot
	# - 3 # phi
	# - 3 # theta
	# - 3 # psi
	# - 10 # p
	# - 10 # q
	# - 10 # r
	lower_bounds:
	- -3 # x
	# - -100 # x_dot
	- -3 # y
	# - -100 # y_dot
	- -0.1 # z
	# - -100 # z_dot
	# - -3 # phi
	# - -3 # theta
	# - -3 # psi
	# - -10 # p
	# - -10 # q
	# - -10 # r