ProCreations's picture
Publish exact native committed Q-learning reproduction
98bc8ca verified
Raw
History Blame Contribute Delete
3.38 kB
{
"assessment": "verified",
"authors_code_commit": "d419a792d83a878b2b32543953fee2874726f4e4",
"authors_code_sha256": "df540300d5f2d4bc7579bb53f065f45f1874a33732f79c54e5378fe2088a7ebb",
"committed_beats_regular_at_all_lengths": true,
"committed_final_fractions": {
"10": 1.0,
"100": 1.0,
"20": 1.0,
"200": 1.0,
"5": 1.0,
"50": 1.0
},
"environment_interactions": 12000000,
"independent_seeded_runs": 12000,
"minimum_final_gap": 0.951,
"official_figure3_curves": {
"committed_k10": {
"final_optimal_count": 1000,
"final_optimal_fraction": 1.0,
"first_t_at_or_above_0_95": 74,
"fraction_t100": 0.995,
"fraction_t1000": 1.0,
"fraction_t500": 1.0
},
"committed_k100": {
"final_optimal_count": 1000,
"final_optimal_fraction": 1.0,
"first_t_at_or_above_0_95": 128,
"fraction_t100": 0.0,
"fraction_t1000": 1.0,
"fraction_t500": 1.0
},
"committed_k20": {
"final_optimal_count": 1000,
"final_optimal_fraction": 1.0,
"first_t_at_or_above_0_95": 99,
"fraction_t100": 0.957,
"fraction_t1000": 1.0,
"fraction_t500": 1.0
},
"committed_k200": {
"final_optimal_count": 1000,
"final_optimal_fraction": 1.0,
"first_t_at_or_above_0_95": 228,
"fraction_t100": 0.0,
"fraction_t1000": 1.0,
"fraction_t500": 1.0
},
"committed_k5": {
"final_optimal_count": 1000,
"final_optimal_fraction": 1.0,
"first_t_at_or_above_0_95": 58,
"fraction_t100": 1.0,
"fraction_t1000": 1.0,
"fraction_t500": 1.0
},
"committed_k50": {
"final_optimal_count": 1000,
"final_optimal_fraction": 1.0,
"first_t_at_or_above_0_95": 77,
"fraction_t100": 0.378,
"fraction_t1000": 1.0,
"fraction_t500": 1.0
},
"regular_k10": {
"final_optimal_count": 40,
"final_optimal_fraction": 0.04,
"first_t_at_or_above_0_95": null,
"fraction_t100": 0.055,
"fraction_t1000": 0.04,
"fraction_t500": 0.041
},
"regular_k100": {
"final_optimal_count": 22,
"final_optimal_fraction": 0.022,
"first_t_at_or_above_0_95": null,
"fraction_t100": 0.048,
"fraction_t1000": 0.022,
"fraction_t500": 0.027
},
"regular_k20": {
"final_optimal_count": 27,
"final_optimal_fraction": 0.027,
"first_t_at_or_above_0_95": null,
"fraction_t100": 0.044,
"fraction_t1000": 0.027,
"fraction_t500": 0.03
},
"regular_k200": {
"final_optimal_count": 34,
"final_optimal_fraction": 0.034,
"first_t_at_or_above_0_95": null,
"fraction_t100": 0.048,
"fraction_t1000": 0.034,
"fraction_t500": 0.033
},
"regular_k5": {
"final_optimal_count": 49,
"final_optimal_fraction": 0.049,
"first_t_at_or_above_0_95": null,
"fraction_t100": 0.054,
"fraction_t1000": 0.049,
"fraction_t500": 0.057
},
"regular_k50": {
"final_optimal_count": 30,
"final_optimal_fraction": 0.03,
"first_t_at_or_above_0_95": null,
"fraction_t100": 0.051,
"fraction_t1000": 0.03,
"fraction_t500": 0.038
}
},
"regular_final_fractions": {
"10": 0.04,
"100": 0.022,
"20": 0.027,
"200": 0.034,
"5": 0.049,
"50": 0.03
}
}