The authors define MDP and NMDP categories, claim their equivalence, and construct new NMDP benchmarks via reversible group-sum and convolution-based history aggregators.
Inferring probabilistic reward machines from non-markovian reward signals for reinforcement learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Constructing Non-Markovian Decision Process via History Aggregator
The authors define MDP and NMDP categories, claim their equivalence, and construct new NMDP benchmarks via reversible group-sum and convolution-based history aggregators.