DI-engine
OpenDILab Decision AI Engine. The Most Comprehensive Reinforcement Learning Framework B.P.
- 3.6k
- Python
- Apache-2.0
- 12 mo ago
OpenDILab Decision AI Engine. The Most Comprehensive Reinforcement Learning Framework B.P.
A curated list of awesome exploration RL resources (continually updated)
This is the pytorch implementation of ICML 2018 paper - Self-Imitation Learning.
Source for the sample efficient tabular RL submission to the 2019 NIPS workshop on Biological and Artificial RL
Thompson-sampling Bayesian router that picks the right LLM per query across quality, cost, and latency. Zero-dependency, TypeScript-first, with exact conjugate posteriors, safe exploration, and bounded regret.
A research lab for off-policy evaluation, exploration, and policy-generated bias in contextual-bandit recommendation systems.
This project focuses on comparing different Reinforcement Learning Algorithms, including monte-carlo, q-learning, lambda q-learning epsilon-greedy variations, etc.
Researching policy-induced observability in recommender systems: when serving policies create self-confirming preference models, and when exploration is worth the cost.