We present an algorithmic approach called Intrinsically Motivated Goal Exploration Processes (IMGEP) to enable similar properties of autonomous or self-supervised learning in machines.
What goals should a multi-goal reinforcement learning agent pursue during training in long-horizon tasks?
Many dynamic processes, including common scenarios in robotic control and reinforcement learning (RL), involve a set of interacting subprocesses.
In open-ended environments, autonomous learning agents must set their own goals and build their own curriculum through an intrinsically motivated exploration.
This objective encourages the agent to maximize the expected return, as well as to achieve more diverse goals.
Current reinforcement learning (RL) algorithms can be brittle and difficult to use, especially when learning goal-reaching behaviors from sparse rewards.
Current image-based reinforcement learning (RL) algorithms typically operate on the whole image without performing object-level reasoning.
When defining distances, the triangle inequality has proven to be a useful constraint, both theoretically--to prove convergence and optimality guarantees--and empirically--as an inductive bias.