Cong Lu

v-d4rl. Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations

SynthER. Synthetic Experience Replay

intelligent-go-explore. Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models

ACD. Automated Capability Discovery via Foundation Model Self-Exploration

nppac. Code to accompany the paper 'On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations'

conglu1997.

mj_envs. A collection of MuJoCo based environments.

awesome-open-ended. Awesome Open-ended AI

erdos_321_computation. Further computation of R(N) in #321, see https://github.com/teorth/erdosproblems/issues/161.