RAMP maximizes the divergence between an agent's current and past state distributions, a proxy for Shannon entropy, and outperforms several prior exploration methods on continuous-control benchmarks.
R-max-a general polynomial time algorithm for near-optimal reinforcement learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Exploration by Running Away from the Past
RAMP maximizes the divergence between an agent's current and past state distributions, a proxy for Shannon entropy, and outperforms several prior exploration methods on continuous-control benchmarks.