Mykel Kochenderfer, Anthony Corso, Robert Moss, Arec Jamgochian, Johannes Fischer
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
To plan safely in uncertain environments, agents must balance utility with safety constraints. Safe planning problems can be modeled as a chanceconstrained partially observable Markov decision process (CC-POMDP) and solutions often use expensive rollouts or heuristics to estimate the optimal value and action-selection policy. This work introduces the ConstrainedZero policy iteration algorithm that solves CC-POMDPs in belief space by learning neural network approximations of the optimal value and policy with an additional network head that estimates the failure probability given a belief. This failure probability guides safe action selection during online Monte Carlo tree search (MCTS). To avoid overemphasizing search based on the failure estimates, we introduce ∆-MCTS, which uses adaptive conformal inference to update the failure threshold during planning. The approach is tested on a safety-critical POMDP benchmark, an aircraft collision avoidance system, and the sustainability problem of safe CO 2 storage. Results show that by separating safety constraints from the objective we can achieve a target level of safety without optimizing the balance between rewards and costs.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2405.00644")
get_code_for_paper("2405.00644")
have("2405.00644")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2405.00644.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2405.00644)
Connect an agent — have() is free.