Skip to content
conftrace_

hindsight replay

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

self-improving language models (1) general intelligence (1) prioritized experience replay (1) neuro-symbolic approach (1) goal-conditioned reinforcement learning (1) hindsight experience replay (1) sparse reward (1) program synthesis (1) expectation maximization (1) policy optimization (1)

Papers

CodeIt: Self-Improving Language Models with Prioritized Hindsight Replay ICML 2024 Hindsight Expectation Maximization for Goal-conditioned Reinforcement Learning AISTATS 2021