Publication | Open Access
Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning
67
Citations
0
References
2018
Year
Artificial IntelligenceReward FunctionEngineeringMachine LearningGame TheoryOff-policy Reinforcement LearningIntelligent SystemsBiasReward BiasRobot LearningImitation LearningCognitive ScienceAutonomous LearningReward FunctionsAction Model LearningSequential Decision MakingComputer ScienceExploration V ExploitationReward HackingAdversarial Imitation LearningAddressing Sample InefficiencyDeep Reinforcement Learning
We identify two issues with the family of algorithms based on the Adversarial Imitation Learning framework. The first problem is implicit bias present in the reward functions used in these algorithms. While these biases might work well for some environments, they can also lead to sub-optimal behavior in others. Secondly, even though these algorithms can learn from few expert demonstrations, they require a prohibitively large number of interactions with the environment in order to imitate the expert for many real-world applications. In order to address these issues, we propose a new algorithm called Discriminator-Actor-Critic that uses off-policy Reinforcement Learning to reduce policy-environment interaction sample complexity by an average factor of 10. Furthermore, since our reward function is designed to be unbiased, we can apply our algorithm to many problems without making any task-specific adjustments.