Add JAX PPO ladder v2 expert pass

This commit is contained in:
2026-07-05 02:06:22 +09:00
parent 7fe0bfdcfe
commit 6037b650f3
11 changed files with 854 additions and 3 deletions
+40
View File
@@ -0,0 +1,40 @@
run:
experiment_name: jax-ppo-ladder-v2-balanced
seed: 20260704
learner_seat: 0
total_updates: 250
log_every: 1
checkpoint_every: 10
artifact_root: /mnt/2tbhdd/coolrl-lost-cities-artifacts/ladder-v2
opponent:
name: heuristic_balanced
network:
hidden_size: 512
num_layers: 3
ppo:
batch_games: 8192
rollout_steps: 400
gamma: 1.0
gae_lambda: 0.95
clip_epsilon: 0.2
entropy_coef: 0.01
value_coef: 0.5
max_grad_norm: 0.5
learning_rate: 0.0003
epochs: 4
minibatches: 128
reward:
terminal_scale: 50.0
potential_shaping_initial: 1.0
potential_shaping_final: 0.0
potential_shaping_anneal_steps: 5000000
evaluation:
games: 10000
duplicate: true
shuffle_bank_seed: 20260704
batch_games: 8192
@@ -0,0 +1,40 @@
run:
experiment_name: jax-ppo-ladder-v2-discard-only
seed: 20260704
learner_seat: 0
total_updates: 250
log_every: 1
checkpoint_every: 10
artifact_root: /mnt/2tbhdd/coolrl-lost-cities-artifacts/ladder-v2
opponent:
name: discard_only
network:
hidden_size: 512
num_layers: 3
ppo:
batch_games: 8192
rollout_steps: 400
gamma: 1.0
gae_lambda: 0.95
clip_epsilon: 0.2
entropy_coef: 0.01
value_coef: 0.5
max_grad_norm: 0.5
learning_rate: 0.0003
epochs: 4
minibatches: 128
reward:
terminal_scale: 50.0
potential_shaping_initial: 1.0
potential_shaping_final: 0.0
potential_shaping_anneal_steps: 5000000
evaluation:
games: 10000
duplicate: true
shuffle_bank_seed: 20260704
batch_games: 8192
+40
View File
@@ -0,0 +1,40 @@
run:
experiment_name: jax-ppo-ladder-v2-expert
seed: 20260704
learner_seat: 0
total_updates: 250
log_every: 1
checkpoint_every: 10
artifact_root: /mnt/2tbhdd/coolrl-lost-cities-artifacts/ladder-v2
opponent:
name: heuristic_expert
network:
hidden_size: 512
num_layers: 3
ppo:
batch_games: 8192
rollout_steps: 400
gamma: 1.0
gae_lambda: 0.95
clip_epsilon: 0.2
entropy_coef: 0.01
value_coef: 0.5
max_grad_norm: 0.5
learning_rate: 0.0003
epochs: 4
minibatches: 128
reward:
terminal_scale: 50.0
potential_shaping_initial: 1.0
potential_shaping_final: 0.0
potential_shaping_anneal_steps: 5000000
evaluation:
games: 10000
duplicate: true
shuffle_bank_seed: 20260704
batch_games: 8192
+40
View File
@@ -0,0 +1,40 @@
run:
experiment_name: jax-ppo-ladder-v2-exploiter
seed: 20260705
learner_seat: 0
total_updates: 250
log_every: 1
checkpoint_every: 10
artifact_root: /mnt/2tbhdd/coolrl-lost-cities-artifacts/ladder-v2
opponent:
name: ladder_v2_gate3_checkpoint_frozen
network:
hidden_size: 512
num_layers: 3
ppo:
batch_games: 8192
rollout_steps: 400
gamma: 1.0
gae_lambda: 0.95
clip_epsilon: 0.2
entropy_coef: 0.01
value_coef: 0.5
max_grad_norm: 0.5
learning_rate: 0.0003
epochs: 4
minibatches: 128
reward:
terminal_scale: 50.0
potential_shaping_initial: 1.0
potential_shaping_final: 0.0
potential_shaping_anneal_steps: 5000000
evaluation:
games: 10000
duplicate: true
shuffle_bank_seed: 20260704
batch_games: 8192