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.
The surprising creativity of digital evolution: A col- lection of anecdotes from the evolutionary computation and artificial life research communities
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
Agentic LLM collectives are proposed as natural-language-interpretable computational substrates for ALife research.
A screening rule skips evolutionary outer loops when the ratio of best single-shot gain to best cheap gain meets or exceeds 90%, validated on pre-registered lab cases where the gate fired and loops were abandoned.
Proposes a classification schema for AI failures drawn from historical cases to improve incident response and guide risk assessment in development.
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.
-
Conversable Complexity: Agentic LLM Collectives as Interpretable Substrates
Agentic LLM collectives are proposed as natural-language-interpretable computational substrates for ALife research.
-
Knowing in Advance When an Evolutionary Outer Loop Will Not Help: A Pre-Registered Cheap-Baseline Screening Rule
A screening rule skips evolutionary outer loops when the ratio of best single-shot gain to best cheap gain meets or exceeds 90%, validated on pre-registered lab cases where the gate fired and loops were abandoned.
-
Classification Schemas for Artificial Intelligence Failures
Proposes a classification schema for AI failures drawn from historical cases to improve incident response and guide risk assessment in development.