Did I do that? Blame as a means to identify controlled effects in reinforcement learning
This addresses a bottleneck in reinforcement learning for agents by providing a novel intrinsic motivator, though it is incremental as it builds on existing exploration methods.
The paper tackled the problem of identifying controllable effects in reinforcement learning by proposing the Controlled Effect Network (CEN), an unsupervised method based on counterfactual blame, which accurately identifies controlled effects and, when integrated into exploration, achieves substantially better performance than action-prediction models.
Identifying controllable aspects of the environment has proven to be an extraordinary intrinsic motivator to reinforcement learning agents. Despite repeatedly achieving State-of-the-Art results, this approach has only been studied as a proxy to a reward-based task and has not yet been evaluated on its own. Current methods are based on action-prediction. Humans, on the other hand, assign blame to their actions to decide what they controlled. This work proposes Controlled Effect Network (CEN), an unsupervised method based on counterfactual measures of blame to identify effects on the environment controlled by the agent. CEN is evaluated in a wide range of environments showing that it can accurately identify controlled effects. Moreover, we demonstrate CEN's capabilities as intrinsic motivator by integrating it in the state-of-the-art exploration method, achieving substantially better performance than action-prediction models.