Potential-based reward shaping for knowledge-based, multi-agent reinforcement learning
PulseAugur coverage of Potential-based reward shaping for knowledge-based, multi-agent reinforcement learning — every cluster mentioning Potential-based reward shaping for knowledge-based, multi-agent reinforcement learning across labs, papers, and developer communities, ranked by signal.
-
New Locally-Guided Actor-Critic method improves goal-conditioned reinforcement learning
Researchers have introduced a new method called Locally-Guided Actor-Critic (LG-AC) to address challenges in goal-conditioned reinforcement learning, particularly with long time horizons and sparse rewards. Existing tec…
-
New DynCur-Geo framework enhances UAV geo-localization with dynamic rewards
Researchers have developed DynCur-Geo, a novel dynamic curiosity framework designed to improve active geo-localization for unmanned aerial vehicles (UAVs). This system dynamically adjusts intrinsic reward weights based …
-
UAV navigation enhanced with RL, safety functions
Researchers have developed a novel approach for autonomous UAV navigation that enhances both speed and safety. This method combines reinforcement learning with potential-based reward shaping, control Lyapunov functions,…