Empathic DQN augments DQN value estimates with an empathy term computed by swapping the learning agent into other agents' situations, reducing collateral harms in two gridworld proof-of-concept environments.
Trial without error: Towards safe reinforce- ment learning via human intervention
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Towards Empathic Deep Q-Learning
Empathic DQN augments DQN value estimates with an empathy term computed by swapping the learning agent into other agents' situations, reducing collateral harms in two gridworld proof-of-concept environments.