19 citations · 123 across the 25 of their papers we have counts for
9 papers · 1 filter
Parametrically Retargetable Decision-Makers Tend To Seek Power
Alexander Matt Turner, Prasad Tadepalli
If capable AI agents are generally incentivized to seek power in service of the objectives we specify for them, then these systems will pose enormous risks, in addition to enormous…
Formalizing the Problem of Side Effect Regularization
Alexander Matt Turner, Aseem Saxena, Prasad Tadepalli
AI objectives are often hard to specify properly. Some approaches tackle this problem by regularizing the AI's side effects: Agents must weigh off "how much of a mess they make" wi…
Dynamic probabilistic logic models for effective abstractions in RL
Harsha Kokel, Arjun Manoharan, Sriraam Natarajan +2
State abstraction enables sample-efficient learning and better task transfer in complex reinforcement learning environments. Recently, we proposed RePReL (Kokel et al. 2021), a hie…
Avoiding Side Effects in Complex Environments
Alexander Matt Turner, Neale Ratzlaff, Prasad Tadepalli
Reward function specification can be difficult. Rewarding the agent for making a widget may be easy, but penalizing the multitude of possible negative side effects is hard. In toy…
Optimal Policies Tend to Seek Power
Alexander Matt Turner, Logan Smith, Rohin Shah +2
Some researchers speculate that intelligent reinforcement learning (RL) agents would be incentivized to seek resources and power in pursuit of their objectives. Other researchers p…
The Choice Function Framework for Online Policy Improvement
Murugeswari Issakkimuthu, Alan Fern, Prasad Tadepalli
There are notable examples of online search improving over hand-coded or learned policies (e.g. AlphaZero) for sequential decision making. It is not clear, however, whether or not…
Conservative Agency via Attainable Utility Preservation
Alexander Matt Turner, Dylan Hadfield-Menell, Prasad Tadepalli
Reward functions are easy to misspecify; although designers can make corrections after observing mistakes, an agent pursuing a misspecified reward function can irreversibly change…
Solving Relational MDPs with Exogenous Events and Additive Rewards
S. Joshi, R. Khardon, P. Tadepalli +2
We formalize a simple but natural subclass of service domains for relational planning problems with object-centered, independent exogenous events and additive rewards capturing, fo…
A Formal Framework for Speedup Learning from Problems and Solutions
P. Tadepalli, B. K. Natarajan
Speedup learning seeks to improve the computational efficiency of problem solving with experience. In this paper, we develop a formal framework for learning efficient problem solvi…