PPO playing impala-PongNoFrameskip-v4 from https://github.com/sgoodfriend/rl-algo-impls/tree/e47a44c4d891f48885af0b1605b30d19fc67b5af
be9c115
| CartPole-v1: &cartpole-defaults | |
| n_timesteps: !!float 5e4 | |
| env_hyperparams: | |
| rolling_length: 50 | |
| policy_hyperparams: | |
| hidden_sizes: [256, 256] | |
| algo_hyperparams: | |
| learning_rate: !!float 2.3e-3 | |
| batch_size: 64 | |
| buffer_size: 100000 | |
| learning_starts: 1000 | |
| gamma: 0.99 | |
| target_update_interval: 10 | |
| train_freq: 256 | |
| gradient_steps: 128 | |
| exploration_fraction: 0.16 | |
| exploration_final_eps: 0.04 | |
| eval_params: | |
| step_freq: !!float 1e4 | |
| CartPole-v0: | |
| <<: *cartpole-defaults | |
| n_timesteps: !!float 4e4 | |
| MountainCar-v0: | |
| n_timesteps: !!float 1.2e5 | |
| env_hyperparams: | |
| rolling_length: 50 | |
| policy_hyperparams: | |
| hidden_sizes: [256, 256] | |
| algo_hyperparams: | |
| learning_rate: !!float 4e-3 | |
| batch_size: 128 | |
| buffer_size: 10000 | |
| learning_starts: 1000 | |
| gamma: 0.98 | |
| target_update_interval: 600 | |
| train_freq: 16 | |
| gradient_steps: 8 | |
| exploration_fraction: 0.2 | |
| exploration_final_eps: 0.07 | |
| Acrobot-v1: | |
| n_timesteps: !!float 1e5 | |
| env_hyperparams: | |
| rolling_length: 50 | |
| policy_hyperparams: | |
| hidden_sizes: [256, 256] | |
| algo_hyperparams: | |
| learning_rate: !!float 6.3e-4 | |
| batch_size: 128 | |
| buffer_size: 50000 | |
| learning_starts: 0 | |
| gamma: 0.99 | |
| target_update_interval: 250 | |
| train_freq: 4 | |
| gradient_steps: -1 | |
| exploration_fraction: 0.12 | |
| exploration_final_eps: 0.1 | |
| LunarLander-v2: | |
| n_timesteps: !!float 5e5 | |
| env_hyperparams: | |
| rolling_length: 50 | |
| policy_hyperparams: | |
| hidden_sizes: [256, 256] | |
| algo_hyperparams: | |
| learning_rate: !!float 1e-4 | |
| batch_size: 256 | |
| buffer_size: 100000 | |
| learning_starts: 10000 | |
| gamma: 0.99 | |
| target_update_interval: 250 | |
| train_freq: 8 | |
| gradient_steps: -1 | |
| exploration_fraction: 0.12 | |
| exploration_final_eps: 0.1 | |
| max_grad_norm: 0.5 | |
| eval_params: | |
| step_freq: 25_000 | |
| _atari: &atari-defaults | |
| n_timesteps: !!float 1e7 | |
| env_hyperparams: | |
| frame_stack: 4 | |
| no_reward_timeout_steps: 1_000 | |
| no_reward_fire_steps: 500 | |
| n_envs: 8 | |
| vec_env_class: "subproc" | |
| algo_hyperparams: | |
| buffer_size: 100000 | |
| learning_rate: !!float 1e-4 | |
| batch_size: 32 | |
| learning_starts: 100000 | |
| target_update_interval: 1000 | |
| train_freq: 8 | |
| gradient_steps: 2 | |
| exploration_fraction: 0.1 | |
| exploration_final_eps: 0.01 | |
| eval_params: | |
| deterministic: false | |
| PongNoFrameskip-v4: | |
| <<: *atari-defaults | |
| n_timesteps: !!float 2.5e6 | |