mischievers
/

openfront-rl-agent

Reinforcement Learning

Model card Files Files and versions

openfront-rl-agent / best_model.pt

Commit History

Update best_model.pt to v18b (obs_dim=96, 512-512-256, reward=0.584, loss penalty)

2e8eda4
verified

JoshuaFreeman commited on Apr 5

Update best_model.pt to v17 (obs_dim=80, best_reward=0.535)

9d3b760
verified

JoshuaFreeman commited on Apr 5

Update default best_model.pt to v16

6b5d3a2
verified

JoshuaFreeman commited on Apr 4

v13b (update 1550): normalized elim + winner bonus, vf=0.5, best generalization

2296e2d
verified

JoshuaFreeman commited on Apr 3

v12a: 100% win rate on Easy/2, normalized elimination reward

2d620cc
verified

JoshuaFreeman commited on Apr 3

Upload best_model.pt with huggingface_hub

4d1058c
verified

JoshuaFreeman commited on Apr 3

Upload best_model.pt with huggingface_hub

522b3bc
verified

JoshuaFreeman commited on Apr 2

Upload best_model.pt with huggingface_hub

490c9fe
verified

JoshuaFreeman commited on Apr 2

Upload best_model.pt with huggingface_hub

f46523a
verified

JoshuaFreeman commited on Apr 1

Upload best_model.pt with huggingface_hub

4ddd3b2
verified

JoshuaFreeman commited on Apr 1