conftrace_

meta-gradient learning

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

skill acquisition (1) practice regime (1) practice environment (1) agent practice (1) exploration control (1) soft-constrained reinforcement learning (1) mujoco domain (1) expected return (1) extrinsic reward (1) constraint violation (1)

Papers

Constrained Policy Optimization for Controlled Self-Learning in Conversational AI Systems ACL 2023 Balancing Constraints and Rewards with Meta-Gradient D4PG ICLR 2021 How Should an Agent Practice? AAAI 2020