ABS uses Behavioral Divergence to adaptively scale batch sizes in RL according to policy volatility, enabling effective large-batch large-network training on ALE benchmarks.
N., and Martin, M
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Task diversity along map, object, and hierarchy axes produces local transfer across shifts in a new continual RL benchmark but fails to sustain learning as the number of shifts grows.
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.
FlashSAC improves training speed and final performance of off-policy RL on high-dimensional robot tasks by reducing update frequency, increasing model scale, and bounding norms to limit critic error accumulation.
Eligibility traces in deep RL create a peak bias by amplifying distal TD errors into gradient shocks that fixed-step SGD cannot normalize, leading to overestimation of peak-reward trajectories and a mechanistic account of the peak-end rule.
Targeted changes to policy initialization, critic targets, and return estimation let SAC match PPO performance across legged locomotion tasks in massively parallel simulation.
A C++ Dec-POMDP simulator using data-oriented design and zero-copy PyTorch integration achieves up to 33 million steps per second on a 16-core CPU, enabling multi-agent policy training in minutes with PPO, DQN, and SAC.
Survey unifies the definition of plasticity loss in DRL, taxonomizes over 50 mitigations, identifies evaluation gaps, and finds general regularization often outperforms domain-specific methods.