Alice uses preservation conflicts from failed candidate updates to create class-stratified hypotheses and guide exploration, improving executable world-model learning under prior misalignment.
hub
Diversity is All You Need: Learning Skills without a Reward Function
17 Pith papers cite this work. Polarity classification is still indexing.
17
Pith papers citing it
abstract
Intelligent creatures can explore their environments and learn useful skills without supervision. In this paper, we propose DIAYN ('Diversity is All You Need'), a method for learning useful skills without a reward function. Our proposed method learns skills by maximizing an information theoretic objective using a maximum entropy policy. On a variety of simulated robotic tasks, we show that this simple objective results in the unsupervised emergence of diverse skills, such as walking and jumping. In a number of reinforcement learning benchmark environments, our method is able to learn a skill that solves the benchmark task despite never receiving the true task reward. We show how pretrained skills can provide a good parameter initialization for downstream tasks, and can be composed hierarchically to solve complex, sparse reward tasks. Our results suggest that unsupervised discovery of skills can serve as an effective pretraining mechanism for overcoming challenges of exploration and data efficiency in reinforcement learning.
hub tools
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
Future State Maximisation (FSM) leads to emergent collective motion features like cohesion and co-alignment in agent simulations.
LEO enables efficient all-goals learning in goal-conditioned RL by jointly predicting for all goals in one network pass, yielding >250x speedup over relabelling and better performance on Craftax.
A hierarchical framework extracts implicit safety criteria from crowd preferences and composes them via high-level policy to reduce safety violations in downstream RL tasks without explicit safety rewards.
Ada-Diffuser is a causal diffusion model that jointly learns observed interaction structure and underlying latent dynamics from minimal observations for adaptive planning and policy learning.
MAVIC corrects Bellman backups at instruction boundaries by adjusting the incoming objective and restoring continuation value, enabling consistent estimation under stochastic instruction switching in cooperative MARL.
TAVT improves OOD task generalization in meta-RL by preserving task characteristics in virtual tasks via metric learning and using state regularization.
RL policies decompose into information-regularized primitives that compete by requesting state information amounts, with the greediest one acting, yielding better generalization than flat or hierarchical baselines.
CDAN framework uses diversity exploration and adversarial self-correction for continual RL in continuous control, evaluated on new CAM environment with NSD metric showing 18.35% NSD improvement over baseline.
DECHRL models causal structures and stochastic delay distributions within hierarchical RL and incorporates them into a delay-aware empowerment objective to improve performance under temporal uncertainty.
QHyer replaces return-to-go with a state-conditioned Q-estimator and adds a gated hybrid attention-mamba backbone to achieve state-of-the-art performance in offline goal-conditioned RL on both Markovian and non-Markovian datasets.
An actor-critic RL algorithm for low-rank MDPs achieves improved sample efficiency using solely a policy evaluation oracle.
Hierarchical Behaviour Spaces uses linear combinations of reward functions to induce expressive behavior spaces in hierarchical RL, yielding strong performance on NetHack primarily through better exploration rather than long-term planning.
MoRE improves robot policy success rates by 44 percentage points by distilling mode redirection into weights, matching filtered retraining performance without inference overhead.
QDHUAC is a distributional, target-free QD-RL method that enables stable high-UTD training and competitive performance on Brax locomotion tasks using far fewer environment steps than prior approaches.
Generative model with normalized pairwise distance constraint discovers output space topologies from sparse data and outperforms GANs and VAEs by avoiding mode collapse.