Weighted Bellman Backups for Improved Signal-to-Noise in Q-Updates

Off-policy deep reinforcement learning (RL) has been successful in a range of challenging domains. However, standard off-policy RL algorithms can suffer from low signal and even instability in Q-learning because target values are derived from current Q-estimates, which are often noisy. To mitigate the issue, we propose ensemble-based weighted Bellman backups, which re-weight target Q-values based on uncertainty estimates from a Q-ensemble. We empirically observe that the proposed method stabilizes and improves learning on both continuous and discrete control benchmarks. We also specifically investigate the signal-to-noise aspect by studying environments with noisy rewards, and find that weighted Bellman backups significantly outperform standard Bellman backups. Furthermore, since our weighted Bellman backups rely on maintaining an ensemble, we investigate how weighted Bellman backups interact with other benefits previously derived from ensembles: (a) Bootstrap; (b) UCB Exploration. We show that these different ideas are largely orthogonal and can be fruitfully integrated, together further improving the performance of existing off-policy RL algorithms, such as Soft Actor-Critic and Rainbow DQN, for both continuous and discrete control tasks on both low-dimensional and high-dimensional environments.