Pith. sign in

REVIEW 4 cited by

Discrete and Continuous Action Representation for Practical RL in Video Games

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1912.11077 v1 pith:EVMTCGJX submitted 2019-12-23 cs.LG cs.AIstat.ML

Olivier Delalleau , Maxim Peter , Eloi Alonso , Adrien Logut This is my paper · ORCID
classification cs.LGcs.AIstat.ML
keywords actionsconstraintscontinuousdiscreteflowsgameshybridnormalizing
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

While most current research in Reinforcement Learning (RL) focuses on improving the performance of the algorithms in controlled environments, the use of RL under constraints like those met in the video game industry is rarely studied. Operating under such constraints, we propose Hybrid SAC, an extension of the Soft Actor-Critic algorithm able to handle discrete, continuous and parameterized actions in a principled way. We show that Hybrid SAC can successfully solve a highspeed driving task in one of our games, and is competitive with the state-of-the-art on parameterized actions benchmark tasks. We also explore the impact of using normalizing flows to enrich the expressiveness of the policy at minimal computational cost, and identify a potential undesired effect of SAC when used with normalizing flows, that may be addressed by optimizing a different objective.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Emotion Entanglement and Bayesian Inference for Multi-Dimensional Emotion Understanding

    cs.CL 2026-04 conditional novelty 6.0 of 10

    Hybrid RL-MPC trained on the full hybrid action space parametrizes continuous MPC via discrete rollouts and a critic terminal cost, yielding near-MINLP F1 strategies with recursive feasibility under a structural assumption.

  2. Optimizing Efficiency of Mixed Traffic through Reinforcement Learning: A Topology-Independent Approach and Benchmark

    cs.RO 2025-01 conditional novelty 6.0 of 10

    A decentralized reinforcement learning policy, using only local sensor data, reduces waiting time and raises throughput compared to fixed traffic lights across 444 real-world-shaped intersection and roundabout scenarios.

  3. Hybrid TD3: Overestimation Bias Analysis and Stable Policy Optimization for Hybrid Action Space

    cs.RO 2026-03 conditional novelty 5.0 of 10

    A weighted clipped Q-learning target that averages over discrete action choices makes TD3-style training stable for hybrid-action robot manipulation.

  4. Reward-Adaptive Iterative Discovery: A Case Study on Automated Game Testing for NHL26

    cs.LG 2026-07 conditional novelty 4.0 of 10

    RAID finds multiple diverse game exploits by sequentially training RL agents and masking previously discovered strategies from the reward function.

Pith tools